© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 133895
    Prev
    Next
    INDEX
    Explanations

    dependency array, string search

    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
     कैंपस
    0.40
     خلينا
    0.40
    雩
    0.38
    ева
    0.37
     enth
    0.36
     використа
    0.35
     Bases
    0.35
     ውሃ
    0.35
     संगठन
    0.35
    굼
    0.35
    POSITIVE LOGITS
    rob
    0.44
    ofd
    0.43
     tant
    0.41
    seud
    0.39
     privati
    0.39
     tanto
    0.38
    мати
    0.38
    ataan
    0.38
     nid
    0.37
     zoveel
    0.37
    Activations Density 0.002%

    No Known Activations