© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 155389
    Prev
    Next
    INDEX
    Explanations

    words like friends and breach

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

    if __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_31_width_262k_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
     эсеп
    0.50
    ن
    0.49
    腖
    0.49
    ెండు
    0.49
    酣
    0.48
    うん
    0.48
    ہرے
    0.47
    س
    0.46
    鏖
    0.46
    细菌
    0.46
    POSITIVE LOGITS
    .
    0.59
    and
    0.55
    travel
    0.53
    ।
    0.53
     stranded
    0.53
     traveling
    0.52
    ports
    0.51
     traveled
    0.50
    times
    0.50
    |=
    0.49
    Activations Density 0.000%

    No Known Activations