© 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. 12218
    Prev
    Next
    INDEX
    Explanations

    quoted strings ending

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

    The neuron is strongly activated by numeric tokens (numbers or number-like strings, including dates and floating-point values).

    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
    䢀
    0.72
    耠
    0.69
     追加
    0.68
    㳓
    0.68
     Bergman
    0.66
     आटे
    0.66
     એલ
    0.65
     Ajoutez
    0.63
     肌
    0.63
     初期
    0.63
    POSITIVE LOGITS
    State
    0.66
     "
    0.64
    ;
    0.62
    ="
    0.60
    "
    0.59
    GIS
    0.59
    br
    0.58
    pip
    0.58
    interest
    0.57
    dead
    0.57
    Activations Density 0.000%

    No Known Activations