© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82413
    Prev
    Next
    INDEX
    Explanations

    sentence or question starts

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

    The neuron fires on reader‐directed instructional or directive phrases (e.g. “You may obtain…” or “during regular business hours”).

    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
     GN
    -0.79
     used
    -0.77
     giáo
    -0.75
    мане
    -0.75
    akyti
    -0.74
    ApiProperty
    -0.74
     Leit
    -0.73
     profissionais
    -0.73
    unitOfWork
    -0.71
    News
    -0.71
    POSITIVE LOGITS
     Sequelize
    0.83
     Sébastien
    0.83
     beaux
    0.81
     prunes
    0.81
    Beratung
    0.80
    höhung
    0.80
    atki
    0.79
    쥔
    0.79
    hasNext
    0.79
     graphene
    0.79
    Activations Density 0.000%

    No Known Activations