© 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. 179439
    Prev
    Next
    INDEX
    Explanations

    business names or logins

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

    writing style and clarity

    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
    Poster
    0.49
     Poster
    0.49
    ع
    0.48
    YC
    0.47
    C
    0.47
    '
    0.46
     poster
    0.46
    t
    0.46
    丁寧
    0.45
    НИ
    0.44
    POSITIVE LOGITS
     অবধি
    0.52
     držav
    0.49
     황
    0.48
     হয়ত
    0.48
     агент
    0.47
     কর্প
    0.47
     버
    0.46
     হারা
    0.46
    regulating
    0.46
     엄마
    0.46
    Activations Density 0.000%

    No Known Activations