© 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. 126432
    Prev
    Next
    INDEX
    Explanations

    auto feature names

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

    auto

    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
     automation
    0.68
    א
    0.65
     Automation
    0.64
    ק
    0.64
    ונים
    0.55
    automate
    0.55
     Automated
    0.55
    ΟΥ
    0.55
    Automation
    0.55
     automatis
    0.55
    POSITIVE LOGITS
     bestowed
    0.49
    ätz
    0.45
    {
    0.45
    ural
    0.44
     scop
    0.44
    ifer
    0.43
     явно
    0.43
    bel
    0.43
    icip
    0.43
    ów
    0.42
    Activations Density 0.050%

    No Known Activations