© 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. 73115
    Prev
    Next
    INDEX
    Explanations

    ideas and information

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

    claims, descriptions, and definitions

    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
    ୍କ
    0.50
    ್ಟ
    0.48
    かかる
    0.48
    ྪ
    0.45
     axit
    0.45
     sulfides
    0.44
    ্লিকেশন
    0.44
    quantile
    0.44
    ξε
    0.43
    뻥
    0.43
    POSITIVE LOGITS
     เพื่อน
    0.52
     сопровожда
    0.49
     сочи
    0.48
    Owl
    0.47
     begle
    0.46
     glauben
    0.45
     познакоми
    0.45
     ich
    0.44
     గురించి
    0.44
     Cyp
    0.43
    Activations Density 0.000%

    No Known Activations