© 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-262K
    7. 26698
    Prev
    Next
    INDEX
    Explanations

    more!

    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
     şöyle
    0.37
     petal
    0.37
     as
    0.36
    那我
    0.36
     imediatamente
    0.36
    ション
    0.35
     throng
    0.35
    <0xC2>
    0.35
     තුළ
    0.34
     Bildung
    0.34
    POSITIVE LOGITS
    แต่
    0.53
     enfin
    0.49
     керек
    0.48
     противо
    0.47
    けど
    0.47
     但
    0.46
     اكثر
    0.46
    $-$,
    0.46
     הרבה
    0.46
     coś
    0.46
    Activations Density 0.006%

    No Known Activations