© 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. 12278
    Prev
    Next
    INDEX
    Explanations

    Text HOME to 741741

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

    This neuron activates on numeric tokens (sequences of digits and decimal numbers).

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

    numeric tokens (especially single digits) in academic citations, technical specifications, and structured reference formats.

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

    structured numeric information, especially years, IDs, page ranges, measurements, and other citation- or unit-like numbers in text.

    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
    𝐄
    0.63
     PGE
    0.62
    𝑬
    0.61
     مکمل
    0.60
     Freddie
    0.59
     ساله
    0.58
     FNA
    0.58
     Ана
    0.57
     పాత్ర
    0.57
    শনার
    0.56
    POSITIVE LOGITS
    fo
    0.52
    utt
    0.52
    ifu
    0.52
    ht
    0.50
    ottam
    0.50
     $($
    0.49
    aged
    0.48
    ram
    0.48
    and
    0.47
    Utt
    0.47
    Activations Density 0.036%

    No Known Activations