© 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. 167875
    Prev
    Next
    INDEX
    Explanations

    May annual

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

    alcohol-free, non-alcoholic

    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
    8
    0.53
    ୮
    0.52
    Site
    0.50
    4
    0.50
    ඉ
    0.50
    я
    0.49
    Length
    0.49
    ٨
    0.49
    다
    0.48
    ५
    0.48
    POSITIVE LOGITS
     Drag
    0.49
     केली
    0.48
     Owens
    0.46
     WITHOUT
    0.44
     UIText
    0.44
     Made
    0.44
     Developmental
    0.43
     કરી
    0.43
     Hom
    0.43
    িয়েছেন
    0.42
    Activations Density 0.001%

    No Known Activations