© 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. 25677
    Prev
    Next
    INDEX
    Explanations

    auto features and events

    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
     The
    -0.87
     Santa
    -0.82
    orithmic
    -0.80
    setCellStyle
    -0.80
    Tú
    -0.79
     their
    -0.78
    imte
    -0.76
    allt
    -0.76
    kym
    -0.75
     alky
    -0.75
    POSITIVE LOGITS
    AutoSize
    0.81
    árol
    0.81
    夏休み
    0.81
    x
    0.80
    true
    0.79
    我が家の
    0.78
     Gábor
    0.77
     true
    0.77
    噼
    0.76
     Lubric
    0.75
    Activations Density 0.001%

    No Known Activations