© 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. 60666
    Prev
    Next
    INDEX
    Explanations

    regardless of

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

    The neuron strongly activates on standalone numeric tokens (digits, years, quantities) and related number‐like sequences.

    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
     evidently
    -0.94
     román
    -0.90
     olas
    -0.84
     vertes
    -0.82
     pú
    -0.79
    лександр
    -0.79
    kola
    -0.78
    🔰
    -0.77
     getField
    -0.77
    อื่น
    -0.76
    POSITIVE LOGITS
    bbene
    1.14
    though
    1.02
    cluding
    1.02
    ומר
    0.96
     względu
    0.95
     regelmäßig
    0.94
     afspraak
    0.94
    beit
    0.92
     لیے
    0.89
    --
    0.88
    Activations Density 0.017%

    No Known Activations