© 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. 10718
    Prev
    Next
    INDEX
    Explanations

    function of x

    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
     مؤرشف
    0.31
    ní
    0.31
     ရ
    0.30
     zaji
    0.28
     ekki
    0.28
     Irlanda
    0.28
     မြ
    0.28
     ގ
    0.28
     لا
    0.27
     ހ
    0.27
    POSITIVE LOGITS
     puisque
    0.36
    क्योंकि
    0.33
    ในการ
    0.29
     formality
    0.29
    Because
    0.28
     competence
    0.28
     because
    0.27
    เพราะ
    0.27
     formalized
    0.27
     bằng
    0.27
    Activations Density 0.000%

    No Known Activations