© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 10543
    Prev
    Next
    INDEX
    Explanations

    geographic and demographic data lists

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

    statistics and data sources

    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
    lyPlugin
    0.64
    Despatx
    0.61
    vaegir
    0.57
    Lorsque
    0.57
    เชสเตอร์
    0.57
    ྜ
    0.57
    Droite
    0.55
    MinIntensity
    0.55
    leValue
    0.55
    聝
    0.55
    POSITIVE LOGITS
     data
    0.80
    ,
    0.70
     records
    0.65
     |
    0.65
    0.65
     D
    0.63
      
    0.63
     of
    0.63
     archive
    0.63
     R
    0.62
    Activations Density 0.006%

    No Known Activations