© 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. 886
    Prev
    Next
    INDEX
    Explanations

    prefix + suffix word completion

    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
    0.41
     alebo
    0.34
     (
    0.34
    mod
    0.33
    ile
    0.32
     vagy
    0.32
    文字列
    0.32
     on
    0.32
    ved
    0.31
    typedef
    0.31
    POSITIVE LOGITS
    ா
    0.48
    و
    0.46
    ہ
    0.45
    ي
    0.44
    ו
    0.44
    ა
    0.44
    ل
    0.42
    ד
    0.42
    י
    0.42
    િ
    0.42
    Activations Density 0.302%

    No Known Activations