© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92727
    Prev
    Next
    INDEX
    Explanations

    Rewrite rules

    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
    standalone
    -0.77
     standing
    -0.68
    tungs
    -0.67
    鹸
    -0.66
    Album
    -0.66
    Standing
    -0.66
    STANDING
    -0.66
     Standing
    -0.65
     Stand
    -0.65
    estar
    -0.64
    POSITIVE LOGITS
    Deus
    0.70
     FACT
    0.67
    iecie
    0.66
    artements
    0.65
    体
    0.63
    づく
    0.63
     LUCK
    0.63
    endl
    0.63
    getTask
    0.62
     IFS
    0.62
    Activations Density 0.081%

    No Known Activations