© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 33975
    Prev
    Next
    INDEX
    Explanations

    Google's infrastructure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     گیرد
    0.42
     TESTING
    0.40
    ণার
    0.40
     ಸರ್
    0.39
    時
    0.39
    ");//
    0.39
    ण्यास
    0.39
    test
    0.39
    為
    0.39
    ००
    0.38
    POSITIVE LOGITS
    殊
    0.39
     Gesicht
    0.39
     Puma
    0.38
    reeks
    0.38
    로운
    0.38
     Suff
    0.38
    Ultimately
    0.37
    Suff
    0.37
     Officer
    0.37
     Medici
    0.37
    Activations Density 0.001%

    No Known Activations