© 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. 32019
    Prev
    Next
    INDEX
    Explanations

    AG code, cells, celebrated, following

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

    patterns and descriptions

    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
     Spann
    0.46
    льнай
    0.46
    Sud
    0.45
     그렇
    0.45
    锥
    0.45
    اللي
    0.44
    鹜
    0.43
     ইসলামী
    0.43
    対象
    0.43
    Saturation
    0.43
    POSITIVE LOGITS
    elligence
    0.43
    
    0.43
     by
    0.42
    ்க
    0.42
     experimentally
    0.40
    playerCards
    0.40
     توسط
    0.39
    ردن
    0.39
     attacking
    0.39
    ہ
    0.39
    Activations Density 0.000%

    No Known Activations