© 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. 40-GEMMASCOPE-2-RES-262K
    7. 7820
    Prev
    Next
    INDEX
    Explanations

    manifest version

    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
    ραγ
    0.34
     Rollins
    0.34
     ው
    0.33
    ymethyl
    0.33
     Vav
    0.32
    𝕆
    0.32
    javax
    0.31
    系
    0.31
     divisible
    0.31
     disregarded
    0.31
    POSITIVE LOGITS
     url
    0.36
    url
    0.35
    permalink
    0.34
    风格
    0.32
    Sup
    0.31
     Url
    0.31
    keywords
    0.31
    امت
    0.29
    hibernate
    0.29
    कै
    0.29
    Activations Density 0.001%

    No Known Activations