© 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. 185033
    Prev
    Next
    INDEX
    Explanations

    highest possible quality

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

    foreign language tokens

    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
    #}
    0.47
     ELECTRO
    0.46
    ＊＊
    0.46
     втра
    0.45
     ZnO
    0.45
     lézards
    0.44
     EFFECTS
    0.44
    Cao
    0.44
     ABSORBED
    0.43
     MILLER
    0.43
    POSITIVE LOGITS
     Тай
    0.47
     وج
    0.46
     סט
    0.46
     de
    0.45
    _{
    0.44
     geen
    0.44
    emmel
    0.42
     váš
    0.42
     networking
    0.41
     الس
    0.41
    Activations Density 0.000%

    No Known Activations