© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32603
    Prev
    Next
    INDEX
    Explanations

    (at your option) licenses

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

    The neuron detects numeric references or quantity words (e.g. actual digits or words like “number”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     tourism
    -0.71
     Zustand
    -0.69
    皖
    -0.69
     Qing
    -0.69
     NEW
    -0.68
     Hammers
    -0.68
    TAT
    -0.68
     TI
    -0.66
     OBJECT
    -0.66
     Fairchild
    -0.66
    POSITIVE LOGITS
    тическое
    0.67
     cánh
    0.65
    dellín
    0.64
     SMD
    0.63
    vartis
    0.63
     وف
    0.63
    zież
    0.63
     EMPIRE
    0.63
    babwe
    0.61
     Inorganic
    0.61
    Activations Density 0.053%

    No Known Activations