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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 7145
    Prev
    Next
    INDEX
    Explanations

    target="_blank"

    np_acts-logits-general · gemini-2.5-flash-lite

    `__name__ == "__main__"`

    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
    ాయ
    0.42
     ró
    0.41
    &)
    0.40
    emorrh
    0.40
    zelfde
    0.40
    MISS
    0.38
    əsi
    0.38
    TIMESTAMPDIFF
    0.38
    AAD
    0.38
    年中
    0.38
    POSITIVE LOGITS
     '__
    0.93
     "__
    0.83
    ="__
    0.82
    __
    0.73
    __:
    0.72
     __
    0.69
    __":
    0.69
     (__
    0.68
    __,
    0.68
    __.
    0.59
    Activations Density 0.000%

    No Known Activations