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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 24052
    Prev
    Next
    INDEX
    Explanations

    good idea to

    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_10/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
     antiguo
    -1.73
    (!__
    -1.70
    mpagne
    -1.63
     ที่
    -1.63
    庹
    -1.59
    isbol
    -1.59
     vermutlich
    -1.55
    對於
    -1.53
     शुर
    -1.50
    Ꮙ
    -1.49
    POSITIVE LOGITS
    搋
    1.67
    $
    1.60
    j
    1.54
    ỽ
    1.53
     几何
    1.52
    の方は
    1.47
     油画
    1.43
    殽
    1.43
     twarzy
    1.41
     宽
    1.41
    Activations Density 0.002%

    No Known Activations