© 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. 239573
    Prev
    Next
    INDEX
    Explanations

    Violet eggs

    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
    ret
    0.49
    mad
    0.47
    -
    0.47
     yellowish
    0.46
     de
    0.46
     Abrams
    0.45
    benz
    0.45
     немно
    0.45
     Bantu
    0.45
    care
    0.44
    POSITIVE LOGITS
    家乐
    0.52
    诋
    0.46
    
    0.45
     Cumhur
    0.45
    伟
    0.45
     മാത്രം
    0.44
    aków
    0.44
    ორცი
    0.44
     นา
    0.44
    ﻲ
    0.44
    Activations Density 0.000%

    No Known Activations