© 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. 101082
    Prev
    Next
    INDEX
    Explanations

    patterns in lists

    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
    n
    0.46
    an
    0.44
    r
    0.43
    smart
    0.43
    D
    0.43
    Pract
    0.41
    G
    0.41
     cleverly
    0.40
    i
    0.40
     smarter
    0.39
    POSITIVE LOGITS
    写入
    0.49
     tussen
    0.48
     గేమ్
    0.48
     espèce
    0.47
    ভিক্ষ
    0.47
    avacan
    0.47
    [,,"
    0.47
     KAL
    0.47
    个人
    0.46
     kal
    0.46
    Activations Density 0.008%

    No Known Activations