© 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. 209981
    Prev
    Next
    INDEX
    Explanations

    garbage collection and recycling

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

    categories and types

    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
    ковский
    0.53
     warrantless
    0.52
    ين
    0.50
    mousePressed
    0.50
     причиной
    0.50
    ጠት
    0.50
    ﺼ
    0.50
     सीड
    0.48
     segni
    0.48
    ял
    0.48
    POSITIVE LOGITS
    ާއި
    0.45
    企业的
    0.45
     ánimo
    0.44
     LastName
    0.43
    Gateway
    0.43
     objectives
    0.43
     frü
    0.42
    itou
    0.42
     목표
    0.42
     ()=>{
    0.42
    Activations Density 0.001%

    No Known Activations