© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4687
    Prev
    Next
    INDEX
    Explanations

    `if __name__ == "__main__":` execution control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
    +"|
    1.11
     reveal
    1.03
    Ẽ
    1.01
    INCREMENT
    0.97
     reaff
    0.96
    INO
    0.95
     illum
    0.95
    ARING
    0.94
    서트
    0.93
    UTO
    0.92
    POSITIVE LOGITS
     довольно
    1.67
     bastante
    1.64
     khá
    1.60
    꽤
    1.57
    かなり
    1.57
     çok
    1.45
     상당히
    1.43
     oldukça
    1.41
    頗
    1.40
    颇
    1.40
    Activations Density 0.205%

    No Known Activations