© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128185
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens (i.e. sequences of digits) wherever they occur in the text.

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

    sports matches with 'v'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    営業
    -0.84
    kony
    -0.77
    iseta
    -0.75
    γά
    -0.73
    アフリカ
    -0.71
    まれて
    -0.71
     Romney
    -0.70
    Gonna
    -0.69
    ADIAN
    -0.69
     EHR
    -0.69
    POSITIVE LOGITS
     második
    0.78
    ULL
    0.76
     also
    0.75
    irected
    0.73
    ей
    0.72
    drivers
    0.72
    tituted
    0.72
    Decl
    0.72
    PopupMenu
    0.71
    otella
    0.71
    Activations Density 0.050%

    No Known Activations