© 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. 93387
    Prev
    Next
    INDEX
    Explanations

    Mobility during

    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
    ircraft
    -0.89
    mce
    -0.81
    вості
    -0.81
    anganan
    -0.79
    тисти
    -0.79
    enuine
    -0.77
    𝗒
    -0.77
     pájaro
    -0.76
    runchy
    -0.76
     δικ
    -0.76
    POSITIVE LOGITS
     Burnley
    0.79
     laboratoire
    0.75
    uno
    0.75
    uru
    0.72
     Rehabilitation
    0.71
    SEX
    0.69
     aire
    0.68
     Ernest
    0.68
    ua
    0.68
     Lock
    0.68
    Activations Density 0.001%

    No Known Activations