© 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. 200678
    Prev
    Next
    INDEX
    Explanations

    Hitchcock touch or Rama

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

    New Delhi, fitness, coffee, always

    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
     archaeologist
    0.48
    kais
    0.46
    ;
    0.46
    cez
    0.43
     হয়ে
    0.43
     रिश्तेदारों
    0.42
    fon
    0.42
    >-
    0.42
     achromatic
    0.42
    gain
    0.41
    POSITIVE LOGITS
    伒
    0.50
     chutes
    0.48
    㱛
    0.48
    🍕
    0.47
    🎮
    0.47
    痘
    0.46
    㿟
    0.45
    🧶
    0.45
    헬
    0.44
     був
    0.44
    Activations Density 0.000%

    No Known Activations