© 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. 229704
    Prev
    Next
    INDEX
    Explanations

    specific items and quantities

    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
     paintball
    0.41
    ,
    0.40
     성
    0.37
     complement
    0.36
    менова
    0.36
    <b>
    0.36
     ma
    0.35
    /
    0.35
     lost
    0.35
     nhờ
    0.35
    POSITIVE LOGITS
    planung
    0.48
     నెల
    0.48
    github
    0.45
    आधी
    0.44
     വിദ
    0.44
    financed
    0.44
     Dienstag
    0.43
    shallow
    0.43
     तैयारी
    0.43
    ここ
    0.43
    Activations Density 0.002%

    No Known Activations