© 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. 107782
    Prev
    Next
    INDEX
    Explanations

    analysis and advice

    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_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
     alight
    -0.84
     Fitted
    -0.83
     unlike
    -0.82
    坏了
    -0.77
     anxiety
    -0.76
     للاس
    -0.73
    にした
    -0.73
    ҳо
    -0.72
     Anlass
    -0.71
     девочек
    -0.71
    POSITIVE LOGITS
    ogram
    0.88
    ſ
    0.87
     xmm
    0.82
     دارای
    0.80
     spirituelle
    0.79
    łucha
    0.77
     repas
    0.76
    legg
    0.76
    InputElement
    0.76
    migiano
    0.75
    Activations Density 0.031%

    No Known Activations