© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76037
    Prev
    Next
    INDEX
    Explanations

    beauty, places, politics

    np_acts-logits-general · gemini-2.5-flash-lite

    reasoning and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ێک
    0.50
     رک
    0.49
     అక్కడ
    0.49
     எங்க
    0.48
     اشت
    0.46
    ية
    0.45
    WMN
    0.45
     अतिक्रमण
    0.45
    ک
    0.45
     castom
    0.43
    POSITIVE LOGITS
     perfume
    0.52
    ros
    0.49
     cologne
    0.49
     UR
    0.47
     uranium
    0.46
     counselor
    0.46
     ribbon
    0.46
     lingerie
    0.46
     ভালোবাসা
    0.45
     relativo
    0.44
    Activations Density 0.000%

    No Known Activations