© 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. 187127
    Prev
    Next
    INDEX
    Explanations

    saving money/effort

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

    concepts and attributes

    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
     Inches
    0.46
    经常
    0.46
    一直
    0.45
    !
    0.45
    lr
    0.43
     Acne
    0.43
     Interviews
    0.42
    '");
    0.41
     Indoor
    0.41
    ła
    0.41
    POSITIVE LOGITS
    結晶
    0.47
    േഷ്
    0.47
     cikin
    0.45
    ਸੀਂ
    0.45
     polypes
    0.45
     stek
    0.44
     critérios
    0.43
     calculer
    0.43
     vantaggio
    0.43
     defocus
    0.43
    Activations Density 0.003%

    No Known Activations