© 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. 136125
    Prev
    Next
    INDEX
    Explanations

    promotion, increase, fonts, classic, approaching, crusher

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

    fix my plumbing

    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
     சுவா
    0.55
    rä
    0.53
     издели
    0.53
     长
    0.49
     количе
    0.49
    rać
    0.49
    Prescott
    0.48
     требо
    0.47
     draped
    0.47
     конфи
    0.47
    POSITIVE LOGITS
     seroton
    0.53
     I
    0.49
     Interrupt
    0.49
     toxin
    0.47
     fluoride
    0.46
     enzyme
    0.46
     spam
    0.46
     shortness
    0.46
     lysine
    0.46
     toxins
    0.46
    Activations Density 0.000%

    No Known Activations