© 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. 99771
    Prev
    Next
    INDEX
    Explanations

    API calls and data stats

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

    The neuron is primarily triggered by numeric tokens—that is, any standalone digit or number in the text.

    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
    EJ
    -0.78
     JSTOR
    -0.75
     Florence
    -0.74
     llam
    -0.74
    kesha
    -0.73
    సి
    -0.73
    ißt
    -0.73
    Sage
    -0.72
     Sabha
    -0.72
    euc
    -0.70
    POSITIVE LOGITS
    sat
    0.86
     SLP
    0.85
    SLP
    0.85
     Cash
    0.81
    Sat
    0.80
     SV
    0.80
    SV
    0.79
    Custo
    0.79
    devel
    0.78
     Lightning
    0.76
    Activations Density 0.027%

    No Known Activations