© 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. 90027
    Prev
    Next
    INDEX
    Explanations

    piggybacking

    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
    Thirty
    -0.75
     Netzwerk
    -0.73
     Thirty
    -0.72
     First
    -0.69
    rivit
    -0.68
    orp
    -0.67
    thirty
    -0.66
    Compile
    -0.66
    First
    -0.66
    Twenty
    -0.64
    POSITIVE LOGITS
    ebay
    0.79
    动画
    0.73
    ревно
    0.71
     kiến
    0.70
    nehmung
    0.69
     potra
    0.69
    Ис
    0.68
     قاب
    0.68
     grandi
    0.67
    arki
    0.66
    Activations Density 0.043%

    No Known Activations