© 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. 26181
    Prev
    Next
    INDEX
    Explanations

    ESLint, logger, auth, new bonds

    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
    不再
    0.46
     Ж
    0.40
    કમાં
    0.39
    Freq
    0.38
    getCurrent
    0.38
    urrence
    0.38
     जियो
    0.38
    ꯤ
    0.38
    Cannon
    0.38
    सेना
    0.38
    POSITIVE LOGITS
    VELOP
    0.47
     semplici
    0.43
    ブリ
    0.42
     Britons
    0.42
     inimes
    0.41
    ク
    0.41
     ಜನರು
    0.40
    ڠ
    0.40
     humains
    0.40
     کرسک
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.