© 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. 106701
    Prev
    Next
    INDEX
    Explanations

    title tags and metadata

    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
    Or
    -1.26
     Or
    -1.22
    OrCreate
    -0.82
    getOr
    -0.81
    或
    -0.71
     或
    -0.69
     Orte
    -0.69
     Ор
    -0.66
     OR
    -0.65
     or
    -0.63
    POSITIVE LOGITS
     Seniors
    0.87
    Seniors
    0.82
    urdu
    0.72
    englisch
    0.70
    Emoji
    0.69
    fordert
    0.68
    seconds
    0.68
    Noch
    0.68
     BAC
    0.67
    शन
    0.67
    Activations Density 0.151%

    No Known Activations