© 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. 98808
    Prev
    Next
    INDEX
    Explanations

    file identifiers and icons

    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
    Opens
    -0.85
     reload
    -0.74
     steigen
    -0.74
     fetching
    -0.73
    openssl
    -0.73
     Stück
    -0.70
     Opens
    -0.69
     bạc
    -0.69
     ČR
    -0.69
    ESTIC
    -0.68
    POSITIVE LOGITS
    upa
    0.78
    タン
    0.70
    qg
    0.69
     electronics
    0.68
     Difficult
    0.68
     strictement
    0.68
     templ
    0.68
    ߌ
    0.68
    melin
    0.67
     通知
    0.66
    Activations Density 0.090%

    No Known Activations