© 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. 12101
    Prev
    Next
    INDEX
    Explanations

    licensed under apache license

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

    The neuron is triggered by standalone numeric tokens (years, version or section numbers, deprecation versions, etc.) in code comments and license headers.

    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
    ttps
    -0.66
    관
    -0.65
    isas
    -0.65
    @"
    -0.64
     papan
    -0.64
     έκ
    -0.64
    ABILITY
    -0.64
    triangle
    -0.63
    >--}}
    -0.62
    istics
    -0.61
    POSITIVE LOGITS
     horaire
    0.73
     payers
    0.72
     ditches
    0.71
    캬
    0.71
    Muff
    0.69
     strpos
    0.69
     пород
    0.68
    NIV
    0.68
    항
    0.68
    ुप
    0.66
    Activations Density 0.073%

    No Known Activations