© 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. 213171
    Prev
    Next
    INDEX
    Explanations

    brands, corresponding, preserve, processed

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

    non-homogeneous equation, issues, volume, personality

    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
    Not in Any Lists

    No Comments

    Negative Logits
     이동
    0.53
     पवन
    0.50
    ിലൂടെ
    0.49
     消
    0.49
    移動
    0.48
    ube
    0.46
    に向けて
    0.45
    ND
    0.45
     জন্মদিন
    0.45
     來
    0.44
    POSITIVE LOGITS
    mentioned
    0.53
     infinites
    0.51
    チャー
    0.49
     exuberant
    0.49
    सम
    0.48
     unimagin
    0.48
     meticul
    0.47
     inconsider
    0.45
     tracts
    0.44
     homology
    0.43
    Activations Density 0.001%

    No Known Activations