© 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. 31-GEMMASCOPE-2-RES-262K
    7. 5441
    Prev
    Next
    INDEX
    Explanations

    structured data separators

    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_31_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
    ಡುವುದ
    0.41
    mathbb
    0.40
    \|$.
    0.40
     এটা
    0.39
     dhinak
    0.38
    所以我
    0.38
    ONOM
    0.38
     thicknesses
    0.37
    টসম্যান
    0.37
     اتارنا
    0.37
    POSITIVE LOGITS
    ،
    0.99
    ，
    0.95
     ,
    0.94
    ,
    0.91
    ၊
    0.88
    、
    0.86
    ፣
    0.72
    *,
    0.71
     ،
    0.67
    
    0.66
    Activations Density 0.081%

    No Known Activations