© 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. 227299
    Prev
    Next
    INDEX
    Explanations

    roux, cook, thickening

    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
    んです
    0.45
    ὥ
    0.44
    上に
    0.44
     hôm
    0.43
    prototype
    0.43
    功
    0.42
    联合国
    0.41
    口
    0.41
    that
    0.41
     charter
    0.41
    POSITIVE LOGITS
    dbox
    0.48
     মনোরম
    0.47
     अर्चना
    0.46
     Satisfaction
    0.45
    arcz
    0.45
     glamorous
    0.45
    과의
    0.44
    ansen
    0.44
    იდან
    0.44
     কিংবা
    0.43
    Activations Density 0.001%

    No Known Activations