© 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. 168532
    Prev
    Next
    INDEX
    Explanations

    mostly words because others follow

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

    profanity ridden tirade

    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
    urtle
    0.52
    ia
    0.50
    Grade
    0.49
    सु
    0.49
    ü
    0.47
     мои
    0.46
    Aprend
    0.46
    Alive
    0.46
    교
    0.46
     спу
    0.45
    POSITIVE LOGITS
     robbery
    0.53
     by
    0.51
     gaping
    0.50
     torrential
    0.49
     bằng
    0.47
     fist
    0.47
     sausage
    0.47
     prudent
    0.46
     stead
    0.46
     biceps
    0.46
    Activations Density 0.001%

    No Known Activations