© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6266
    Prev
    Next
    INDEX
    Explanations

    in preceding phrases

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on floating‐point numbers (numerical tokens with decimals), especially when they appear at the start of a phrase.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the preposition "In" at the beginning of sentences or clauses.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    sentence starts that open with a capitalized preposition or determiner followed immediately by another short function word, as in academic-style “In the/This …” lead‑ins.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Also
    0.84
     Also
    0.79
     همچنین
    0.68
    It
    0.67
    However
    0.67
    And
    0.67
     And
    0.66
     inoltre
    0.66
     таксама
    0.66
    Также
    0.65
    POSITIVE LOGITS
     diesem
    0.89
     unseren
    0.86
     seinen
    0.81
     ihren
    0.78
     первую
    0.78
     November
    0.77
     seinem
    0.77
     welchen
    0.76
    clusion
    0.76
     unserem
    0.76
    Activations Density 0.131%

    No Known Activations