© 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. 117812
    Prev
    Next
    INDEX
    Explanations

    clothing and materials

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

    concrete objects with subsequent states

    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
     ं
    0.53
     conductive
    0.51
     operatives
    0.50
    conductivity
    0.47
     achieves
    0.46
    ylobacter
    0.45
     restricts
    0.45
     optimise
    0.45
    ฏ
    0.45
    ympt
    0.44
    POSITIVE LOGITS
    遇到了
    0.48
    Double
    0.48
    用
    0.46
    ที่มี
    0.46
     που
    0.46
     μαύ
    0.46
     עם
    0.46
    蓝牙
    0.45
    木
    0.45
     với
    0.45
    Activations Density 0.000%

    No Known Activations