© 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. 176224
    Prev
    Next
    INDEX
    Explanations

    Russian income, Separate Peace, latest technologies

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

    opening statements, names, descriptions

    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
    у
    0.50
    being
    0.49
    ما
    0.49
    Keeping
    0.48
    re
    0.47
    ರ್ಯ
    0.46
    have
    0.46
    go
    0.45
    У
    0.45
    Skin
    0.45
    POSITIVE LOGITS
     SAE
    0.47
    etään
    0.46
     letteratura
    0.46
     sugli
    0.45
     pudieran
    0.45
     osmotic
    0.44
     internazionali
    0.44
     سیاسی
    0.43
     anthropology
    0.43
     characterizing
    0.43
    Activations Density 0.001%

    No Known Activations