© 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. 40-GEMMASCOPE-2-RES-65K
    7. 1010
    Prev
    Next
    INDEX
    Explanations

    numbered lists or markers

    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_40_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
     H
    0.47
    ;
    0.44
     Create
    0.43
     Could
    0.43
     dout
    0.43
     A
    0.42
    ::
    0.42
    .)
    0.42
     dolom
    0.42
     июле
    0.42
    POSITIVE LOGITS
    堊
    0.48
    ؍
    0.45
     ആണ്
    0.45
    آ
    0.44
    كشن
    0.43
    ت
    0.43
    襞
    0.42
    ה
    0.42
    ラー
    0.42
    ]-\
    0.42
    Activations Density 0.108%

    No Known Activations