© 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. 200259
    Prev
    Next
    INDEX
    Explanations

    substitute for, confirmed as, knows German, require certification

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

    SELECT COUNT

    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
    ﻻ
    0.52
    හෙ
    0.52
    يت
    0.50
    ણી
    0.49
     esfuerzos
    0.49
    ड्या
    0.48
    ق
    0.48
    垻
    0.48
    ފ
    0.48
    ДИ
    0.46
    POSITIVE LOGITS
    newEvent
    0.43
     न्यू
    0.43
    newL
    0.43
    edt
    0.42
     उल्लेखनीय
    0.42
     Orioles
    0.42
     Phnom
    0.40
     Phillies
    0.40
    etr
    0.40
     Async
    0.40
    Activations Density 0.001%

    No Known Activations