© 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. 91142
    Prev
    Next
    INDEX
    Explanations

    ( MIT License

    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
    orant
    -0.75
    fattning
    -0.74
    合约
    -0.74
    rings
    -0.73
     bundles
    -0.71
    crom
    -0.71
    jazd
    -0.69
    fundamental
    -0.68
    hinder
    -0.66
    curl
    -0.66
    POSITIVE LOGITS
     airbag
    0.74
    kop
    0.70
    xd
    0.69
     spelled
    0.69
    ZW
    0.67
    эро
    0.66
    XD
    0.65
     BBC
    0.65
    icho
    0.63
    inu
    0.63
    Activations Density 0.070%

    No Known Activations