© 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. 174389
    Prev
    Next
    INDEX
    Explanations

    category tags

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

    OS commands and user requests

    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
    READ
    0.44
    i
    0.41
     Idha
    0.41
     sailed
    0.41
     ಮು
    0.40
    uğ
    0.40
    GPa
    0.39
     subtleties
    0.39
     अंत
    0.38
    ð
    0.38
    POSITIVE LOGITS
     віднов
    0.53
     الور
    0.50
     continuando
    0.50
    堌
    0.47
    мов
    0.46
    avit
    0.46
    追加
    0.45
    foro
    0.45
     objectif
    0.45
     chien
    0.45
    Activations Density 0.001%

    No Known Activations