© 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. 244479
    Prev
    Next
    INDEX
    Explanations

    foreign language or script

    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
    贈
    0.43
     समितियों
    0.42
    Ig
    0.40
    lesssim
    0.40
    gtrsim
    0.40
     benef
    0.39
     會
    0.39
    也會
    0.38
    Mit
    0.38
    alimentation
    0.38
    POSITIVE LOGITS
    स्कृतिक
    0.48
     exposes
    0.48
     flawlessly
    0.48
     entree
    0.46
     impeccable
    0.46
    嫖
    0.44
     entrée
    0.44
     fascinated
    0.43
     kebak
    0.43
     фаса
    0.42
    Activations Density 0.000%

    No Known Activations