© 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-65K
    7. 19758
    Prev
    Next
    INDEX
    Explanations

    less than

    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_65k_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
     UpdateWindow
    0.50
     говорили
    0.48
     เหมือน
    0.48
     opak
    0.47
     łat
    0.47
     ማ
    0.46
     suffisante
    0.46
     отно
    0.45
     À
    0.45
     captures
    0.45
    POSITIVE LOGITS
    of
    0.47
     daarbij
    0.47
    有一些
    0.44
    野
    0.42
    potential
    0.42
    tenberg
    0.42
    支援
    0.42
    宝石
    0.40
    等
    0.40
    pressed
    0.39
    Activations Density 0.000%

    No Known Activations