© 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. 33474
    Prev
    Next
    INDEX
    Explanations

    by ACCESS

    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
    Browser
    -0.71
    localized
    -0.69
    Jeremy
    -0.69
     Jeremy
    -0.68
     Heated
    -0.66
     Italijani
    -0.64
    Http
    -0.64
     peningkatan
    -0.64
     Ahmed
    -0.63
    ishman
    -0.63
    POSITIVE LOGITS
    С
    0.78
    Население
    0.77
    componentWill
    0.77
    Bypass
    0.76
     Hamma
    0.73
    clang
    0.73
    Symfony
    0.71
    ℃
    0.69
     selon
    0.69
    禟
    0.69
    Activations Density 0.525%

    No Known Activations