© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1033
    Prev
    Next
    INDEX
    Explanations

    code imports and declarations

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

    The neuron strongly activates on numeric tokens and number‐related strings (years, percentages, measurements, etc.).

    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
     boutons
    0.61
    <unused15>
    0.59
     precludes
    0.59
     questa
    0.57
     pocos
    0.57
     ancillary
    0.56
     HART
    0.56
     ニュー
    0.56
     winch
    0.55
     poucos
    0.55
    POSITIVE LOGITS
    0.56
    Python
    0.54
    创建一个
    0.54
    String
    0.52
    Temperature
    0.52
    A
    0.52
    Microsoft
    0.51
    Autom
    0.50
    S
    0.50
    Emoji
    0.49
    Activations Density 0.022%

    No Known Activations