© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 23148
    Prev
    Next
    INDEX
    Explanations

    punctuation and appositive clauses

    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
    س
    0.84
    t
    0.82
    e
    0.74
    s
    0.72
    ج
    0.67
    ്രീ
    0.65
    g
    0.64
    لى
    0.64
    ك
    0.64
    𝟬
    0.63
    POSITIVE LOGITS
    ,
    0.87
    '
    0.76
    
    0.68
    ın
    0.63
    ;
    0.63
     I
    0.57
    ↵
    0.57
    nya
    0.56
    ün
    0.55
    us
    0.55
    Activations Density 0.076%

    No Known Activations