© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99341
    Prev
    Next
    INDEX
    Explanations

    declarative statements or descriptions

    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
     πρ
    -1.02
    ૉ
    -1.02
     ediyor
    -1.00
     gyere
    -0.99
     fonctionnent
    -0.96
    computa
    -0.95
     méret
    -0.95
    を中心に
    -0.95
     octobre
    -0.94
    NOOP
    -0.93
    POSITIVE LOGITS
     [
    1.00
    荒
    0.95
     gênero
    0.88
     deserved
    0.87
    Activité
    0.86
    _;
    0.86
    TokenNameEQUAL
    0.85
     predicted
    0.85
    íp
    0.85
     дев
    0.85
    Activations Density 0.017%

    No Known Activations