© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 37997
    Prev
    Next
    INDEX
    Explanations

    permissions and limitations

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

    The neuron activates on numeric tokens (digits and numbers).

    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
    possession
    -0.93
    鉨
    -0.87
    umis
    -0.85
    urna
    -0.82
    kud
    -0.78
    deles
    -0.75
     Kud
    -0.73
     توجه
    -0.73
    netto
    -0.73
    akang
    -0.72
    POSITIVE LOGITS
     prayed
    0.78
    ŏ
    0.75
    ametri
    0.70
    Conce
    0.69
    Amt
    0.68
    操
    0.67
    Enquiries
    0.67
     conceal
    0.66
    uku
    0.66
    ERIES
    0.65
    Activations Density 0.017%

    No Known Activations