© 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. 203096
    Prev
    Next
    INDEX
    Explanations

    die, toast, ®

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

    security requirements

    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
    _
    0.57
    NA
    0.55
    0
    0.49
    8
    0.48
    ardin
    0.46
    ("
    0.46
     reads
    0.45
    ρεία
    0.45
    ural
    0.44
    과
    0.43
    POSITIVE LOGITS
     ක්ර
    0.52
    キュリティ
    0.50
     घिरा
    0.50
     Í
    0.50
     कहीं
    0.49
     ಸಾಕಷ್ಟು
    0.48
     fuer
    0.47
     कही
    0.47
     निवडणूक
    0.47
     退
    0.47
    Activations Density 0.000%

    No Known Activations