© 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. 195657
    Prev
    Next
    INDEX
    Explanations

    days ago or minutes

    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
    ɖ
    0.39
    ﮏ
    0.37
     (**
    0.37
     वर्
    0.36
     CRE
    0.36
     xer
    0.35
     series
    0.35
    दीप
    0.34
    簸
    0.34
     серии
    0.34
    POSITIVE LOGITS
     expedit
    0.40
    赟
    0.39
    瘍
    0.38
    чё
    0.37
    私の
    0.37
     bridge
    0.36
    my
    0.36
    翻訳
    0.36
    find
    0.35
    arel
    0.35
    Activations Density 0.000%

    No Known Activations