© 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. 6946
    Prev
    Next
    INDEX
    Explanations

    javascript and code snippets

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

    importing code libraries

    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
    grunge
    0.37
    Grunge
    0.37
     RADIATION
    0.37
    เวล
    0.36
    ੨
    0.35
     Ecke
    0.35
     Schwarzen
    0.35
    ometime
    0.35
     whining
    0.35
    นาะ
    0.34
    POSITIVE LOGITS
     pokemon
    0.35
     pygame
    0.33
     sql
    0.31
     kafka
    0.30
     game
    0.29
     jwt
    0.29
     sensors
    0.29
     usb
    0.29
    <0xC2>
    0.29
     retrofit
    0.28
    Activations Density 0.000%

    No Known Activations