© 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. 165137
    Prev
    Next
    INDEX
    Explanations

    * followed by first

    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
     যাহ
    0.41
    yaratan
    0.37
    ૪
    0.36
     Creating
    0.35
    ारात
    0.35
    DispatchRequest
    0.34
    ೪
    0.34
    ativa
    0.34
    Carol
    0.34
    ใส่
    0.34
    POSITIVE LOGITS
    ەوە
    0.39
     ।*
    0.38
    Values
    0.38
     donors
    0.38
     пое
    0.38
     Morrissey
    0.38
    ග්
    0.37
     kā
    0.37
     neko
    0.37
     backtrack
    0.37
    Activations Density 0.000%

    No Known Activations