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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 27729
    Prev
    Next
    INDEX
    Explanations

    Red leaves

    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
    ку
    0.44
    Whitespace
    0.42
    اء
    0.42
     curated
    0.41
    Sustainability
    0.41
     THEIR
    0.40
    <0x0D>
    0.40
    ą
    0.39
    //!
    0.39
    🥝
    0.39
    POSITIVE LOGITS
     cenderung
    0.45
    分けて
    0.44
     niños
    0.44
     عمل
    0.43
     Cuando
    0.41
     Difer
    0.41
     Hunde
    0.40
     ۳
    0.40
     በሽታ
    0.40
     stärker
    0.40
    Activations Density 0.044%

    No Known Activations