© 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. 111500
    Prev
    Next
    INDEX
    Explanations

    legal or contractual language

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

    breakdown of types

    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
     комбина
    0.58
    良く
    0.52
     подход
    0.52
    ﻫ
    0.52
     проек
    0.51
     triage
    0.49
     устра
    0.49
     তোলা
    0.49
     любовь
    0.48
    幌
    0.48
    POSITIVE LOGITS
    gub
    0.48
    ոտ
    0.45
    oft
    0.45
    ucz
    0.44
     ergodic
    0.44
    odesmium
    0.44
    legas
    0.43
     accesses
    0.42
    lifetime
    0.42
     Ā
    0.42
    Activations Density 0.000%

    No Known Activations