© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 70234
    Prev
    Next
    INDEX
    Explanations

    sequences of technical or descriptive terms

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

    options, understanding, analysis

    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
    in
    0.62
    Levels
    0.45
    মী
    0.44
     level
    0.43
    ürich
    0.43
    蘇
    0.43
    ασία
    0.43
    爾
    0.42
    ic
    0.42
    level
    0.42
    POSITIVE LOGITS
    rebbero
    0.51
     に対して
    0.49
    чно
    0.48
    ᱸ
    0.48
    мм
    0.47
     ತುಂಬ
    0.47
     हाईवे
    0.47
     يجب
    0.46
     भुव
    0.45
    टरी
    0.45
    Activations Density 0.001%

    No Known Activations