© 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. 184453
    Prev
    Next
    INDEX
    Explanations

    such behavior, the grants

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

    translation, coding, programming, grammar

    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
    ed
    0.49
    ERN
    0.46
    ᅭ
    0.46
     convirtió
    0.44
    dataFormat
    0.44
    CONCLUSIONS
    0.44
    ISION
    0.43
    IS
    0.43
    ິງ
    0.43
    镟
    0.43
    POSITIVE LOGITS
    लता
    0.52
     ощущение
    0.47
     эпоху
    0.47
     رعایت
    0.46
     전혀
    0.45
    ಜ
    0.44
     cramped
    0.44
    acrylate
    0.44
    क्सन
    0.44
    говари
    0.43
    Activations Density 0.000%

    No Known Activations