© 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. 98925
    Prev
    Next
    INDEX
    Explanations

    code and descriptions

    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
     هم
    0.44
    廢
    0.40
    modulation
    0.38
     Rudd
    0.37
    衩
    0.37
     پایان
    0.37
     კომპ
    0.36
    奶
    0.36
     Anand
    0.36
    是否
    0.36
    POSITIVE LOGITS
    ヴィトン
    0.39
     campaigned
    0.38
     VT
    0.37
    ('/:
    0.37
     sa
    0.36
     veritable
    0.36
     contender
    0.36
    knight
    0.35
    芬
    0.34
     biologic
    0.34
    Activations Density 0.000%

    No Known Activations