© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 87080
    Prev
    Next
    INDEX
    Explanations

    policy trigger, analog inputs, exposure setting

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

    states, scope, start

    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
    Negative Logits
     bargains
    0.43
    파
    0.42
    ные
    0.42
     qué
    0.42
    骡
    0.41
    凉
    0.41
    Ꮜ
    0.41
    മ്പ
    0.41
    !');
    0.41
    नाल्ड
    0.41
    POSITIVE LOGITS
     ሽፋን
    0.48
    ﻪ
    0.46
     overly
    0.46
     साड़ी
    0.45
     uptick
    0.45
    categorias
    0.42
    onicus
    0.41
     మరింత
    0.41
     मुख
    0.41
     سرا
    0.41
    Activations Density 0.001%

    No Known Activations