© 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. 6127
    Prev
    Next
    INDEX
    Explanations

    business and technical terms

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

    The neuron detects prominent proper nouns and named entities (e.g. brand names, product names, and place names).

    oai_token-act-pair · o4-miniTriggered 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
     साठी
    0.84
    㑹
    0.84
     котором
    0.83
    ාවිත
    0.83
     których
    0.82
     能
    0.81
     которых
    0.80
     했는데
    0.77
    ἲ
    0.77
    ǜ
    0.77
    POSITIVE LOGITS
     other
    0.74
     fucking
    0.68
     category
    0.68
    ↵
    0.66
    /
    0.66
     x
    0.64
    1
    0.63
     en
    0.63
     j
    0.62
     andere
    0.61
    Activations Density 0.009%

    No Known Activations