© 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. 187004
    Prev
    Next
    INDEX
    Explanations

    north limit, east limit

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

    anyone to modify and deploy

    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
     Bart
    0.47
     সার্টিফিকেট
    0.46
    achtree
    0.46
    cartes
    0.45
     integers
    0.44
    ImagePath
    0.44
     लिमिटेड
    0.43
     इ
    0.43
     Euclidean
    0.43
     হোমিওপ্যাথির
    0.43
    POSITIVE LOGITS
    ปี
    0.45
    ง
    0.43
    🗣
    0.43
    สู่
    0.42
    
    0.42
    炉
    0.42
     roky
    0.41
    ช่วง
    0.41
    อาจ
    0.41
    ร่างกาย
    0.41
    Activations Density 0.000%

    No Known Activations