© 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. 24-GEMMASCOPE-2-RES-16K
    7. 2204
    Prev
    Next
    INDEX
    Explanations

    domestic violence hotline

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

    This neuron activates on standalone numeric tokens—especially multi‐digit or decimal numbers (e.g. prices, measurements, scores).

    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_24_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
    _
    0.64
    -
    0.62
    /
    0.62
    Р
    0.57
    ・
    0.55
    ס
    0.54
    IV
    0.52
    。
    0.52
    ,
    0.50
    ).
    0.49
    POSITIVE LOGITS
     fierc
    0.54
    <unused2177>
    0.54
     کریں
    0.53
     Hoping
    0.50
     remod
    0.49
     పై
    0.49
     garn
    0.48
     możesz
    0.48
    முகச்
    0.47
     പ്രതി
    0.46
    Activations Density 0.013%

    No Known Activations