© 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. 124030
    Prev
    Next
    INDEX
    Explanations

    Cuban Heritage, map worldwide, top village

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

    few-shot prompting

    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
    기도
    0.40
    たた
    0.35
     Bhand
    0.34
     बावजूद
    0.34
    ２
    0.34
    liga
    0.32
     dignitaries
    0.32
    स्प
    0.32
    知識
    0.32
    国防
    0.32
    POSITIVE LOGITS
    &&\
    0.37
     реки
    0.36
    &&
    0.35
     rv
    0.35
    из
    0.34
     mousse
    0.34
    NODE
    0.33
    ステム
    0.33
     লেখার
    0.33
    INFORM
    0.33
    Activations Density 0.157%

    No Known Activations