© 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. 225676
    Prev
    Next
    INDEX
    Explanations

    numbers and foreign words

    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
    Merc
    0.52
    L
    0.50
    M
    0.46
    overall
    0.45
    Opposition
    0.45
    K
    0.44
    클
    0.44
    lego
    0.43
     insgesamt
    0.43
    ்டோ
    0.43
    POSITIVE LOGITS
     để
    0.53
     نئی
    0.52
     ដើម្បី
    0.52
     اپنی
    0.49
    ৰি
    0.47
    荿
    0.46
     Trapez
    0.45
     अपनी
    0.45
     અથવા
    0.45
     щоб
    0.45
    Activations Density 0.001%

    No Known Activations