© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138509
    Prev
    Next
    INDEX
    Explanations

    PHP code and statistics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    се
    0.48
    া
    0.44
    캉
    0.42
    货
    0.42
     ски
    0.41
     грузо
    0.40
     רי
    0.40
    '};
    0.40
    冰箱
    0.39
     преодо
    0.39
    POSITIVE LOGITS
     statistic
    0.44
     dimers
    0.44
     Statistic
    0.42
     Bantu
    0.40
     announced
    0.40
     Announced
    0.40
     délégation
    0.39
     Bourd
    0.38
     officially
    0.38
     hibiscus
    0.38
    Activations Density 0.003%

    No Known Activations