Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 223921
    Prev
    Next
    INDEX
    Explanations

    polygon and attacker

    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_40_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
     Bingo
    0.42
     обладают
    0.41
     চৈত
    0.41
    mathemat
    0.40
    Mathematical
    0.40
     banquet
    0.39
     bingo
    0.39
    $;
    0.38
    Signup
    0.38
    ချိန်
    0.38
    POSITIVE LOGITS
     شناس
    0.39
     indiscrimin
    0.39
     hypocrisy
    0.38
     hyphen
    0.38
     automatis
    0.38
     coalesce
    0.38
     polož
    0.37
    isph
    0.36
     горизонта
    0.36
    postas
    0.36
    Activations Density 0.002%

    No Known Activations