© 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. 25871
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

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

    questions and options

    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
    _{,
    0.39
    Ꮑ
    0.39
     रंगों
    0.38
    ForRule
    0.37
    理由
    0.37
     Refs
    0.36
    ธ์
    0.36
    铒
    0.36
     verlassen
    0.36
     réf
    0.35
    POSITIVE LOGITS
    myfile
    0.43
    oga
    0.42
     timedelta
    0.42
    ⌄
    0.41
    Workflow
    0.41
     captures
    0.40
    osha
    0.40
    Overview
    0.40
    ografie
    0.40
     পূর্বা
    0.40
    Activations Density 0.001%

    No Known Activations