© 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. 56770
    Prev
    Next
    INDEX
    Explanations

    washing, signs, eyelash extensions

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

    categories and technical terms

    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
    the
    0.56
    CHAT
    0.50
    聊
    0.50
    script
    0.48
    ವಾ
    0.47
     disability
    0.47
    Università
    0.45
    PATH
    0.45
     census
    0.45
     Disability
    0.45
    POSITIVE LOGITS
     tỏ
    0.52
     Eulerian
    0.47
     ය
    0.45
     extrémité
    0.45
     visibly
    0.45
     உறுதி
    0.44
     стоя
    0.44
     achieves
    0.44
     stressing
    0.44
     иногда
    0.43
    Activations Density 0.000%

    No Known Activations