© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1100
    Prev
    Next
    INDEX
    Explanations

    study groups and partners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     сове
    0.47
     जबाब
    0.45
     primaryStage
    0.45
    菏
    0.44
     വിഷയ
    0.44
    ఠ
    0.43
     roundtable
    0.43
     kiles
    0.42
     SAFE
    0.42
    লেম
    0.42
    POSITIVE LOGITS
     Guzman
    0.46
     Traff
    0.42
     /
    0.41
     Pressed
    0.41
     Addition
    0.41
     '
    0.40
    ua
    0.39
    aca
    0.39
     Sources
    0.39
     Bann
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.