© 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. 201224
    Prev
    Next
    INDEX
    Explanations

    limiting the generality of

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

    pure water, classic student

    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
    الأ
    0.52
    Чер
    0.52
    רים
    0.51
    穀
    0.51
    噓
    0.50
    هل
    0.50
    朱
    0.50
    رمز
    0.50
    འི་
    0.49
    長
    0.48
    POSITIVE LOGITS
     生命周期
    0.47
    oy
    0.46
     riparian
    0.46
     huit
    0.45
     를
    0.44
     отправи
    0.44
    om
    0.44
    an
    0.43
    ug
    0.43
     결국
    0.43
    Activations Density 0.001%

    No Known Activations