© 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. 11908
    Prev
    Next
    INDEX
    Explanations

    .

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

    The neuron flags standalone numeric tokens (e.g. version numbers, copyright years, large integers) in source‐code comments and 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
     SAB
    -0.71
    malıdır
    -0.67
     oficialmente
    -0.66
    干净
    -0.66
    昴
    -0.65
    UPDATED
    -0.65
     cela
    -0.64
     Immunol
    -0.64
    )}+
    -0.63
    dispon
    -0.62
    POSITIVE LOGITS
     millis
    0.75
    ains
    0.68
     richesse
    0.68
    afar
    0.67
     Tertiary
    0.67
     синте
    0.66
    unordered
    0.66
     projectId
    0.65
     sexo
    0.65
    项目
    0.65
    Activations Density 0.060%

    No Known Activations