© 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. 85116
    Prev
    Next
    INDEX
    Explanations

    planning and recovery context

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

    describing physical states and interactions

    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
     Menschen
    0.63
     людини
    0.55
     людьми
    0.55
    chtigen
    0.55
    𝘫
    0.54
     людям
    0.54
    }$.)
    0.53
     человеку
    0.53
     человеком
    0.53
     člov
    0.53
    POSITIVE LOGITS
     veto
    0.53
    ↵
    0.51
     Equation
    0.49
     L
    0.48
     adoption
    0.48
     NAC
    0.47
     Naval
    0.46
    '
    0.46
    の設定
    0.46
      
    0.45
    Activations Density 0.000%

    No Known Activations