© 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. 173921
    Prev
    Next
    INDEX
    Explanations

    Crime Statistics

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

    conditional explanations

    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
     effluents
    0.53
    流量
    0.51
    %
    0.50
    Relative
    0.48
     malignant
    0.48
     chronically
    0.47
     seeds
    0.47
     phospholipids
    0.47
     metabolized
    0.47
     debris
    0.46
    POSITIVE LOGITS
     നട
    0.54
    ಞ
    0.54
    🏪
    0.53
     télévision
    0.51
    віч
    0.48
     തിരിച്ച
    0.48
    द्धि
    0.48
     ልዩ
    0.47
    ột
    0.47
    ttet
    0.47
    Activations Density 0.001%

    No Known Activations