© 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. 10-GEMMASCOPE-RES-131K
    7. 19422
    Prev
    Next
    INDEX
    Explanations

    narratives and personal accounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     said
    -1.91
     the
    -1.66
     such
    -1.38
     __
    -1.36
     called
    -1.33
     si
    -1.32
     is
    -1.30
     to
    -1.30
     offered
    -1.23
     ____
    -1.23
    POSITIVE LOGITS
     案例
    1.65
     設置
    1.52
     моего
    1.48
     моих
    1.45
     補
    1.45
     of
    1.44
     验证
    1.41
    ඬ
    1.41
     capuz
    1.41
     amortecedor
    1.41
    Activations Density 0.029%

    No Known Activations