© 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. 64060
    Prev
    Next
    INDEX
    Explanations

    cities, people, and code elements

    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
     fleurs
    -0.77
    tionalität
    -0.76
     repeat
    -0.75
    oxia
    -0.75
    ském
    -0.75
     &=&
    -0.72
     decadent
    -0.72
     THEN
    -0.72
    ற
    -0.71
     mettez
    -0.70
    POSITIVE LOGITS
    lys
    0.83
    ofd
    0.81
    掻
    0.78
     Arn
    0.77
    úa
    0.76
    Pis
    0.76
    ちょこ
    0.75
    锹
    0.74
    くっ
    0.73
    Psychological
    0.73
    Activations Density 0.001%

    No Known Activations