© 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. 31-GEMMASCOPE-2-RES-262K
    7. 75944
    Prev
    Next
    INDEX
    Explanations

    identifiers followed by punctuation

    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/layer_31_width_262k_l0_medium
    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
     היי
    0.46
     חש
    0.45
     ต่อ
    0.45
    පු
    0.43
     Här
    0.43
    Ǧ
    0.42
    už
    0.41
    ↵
    0.41
     pharmacological
    0.40
    Í
    0.40
    POSITIVE LOGITS
    ни
    0.54
    ками
    0.54
    ств
    0.51
    сть
    0.50
    ंना
    0.48
    том
    0.47
    ант
    0.47
    ों
    0.47
    мое
    0.47
    стю
    0.46
    Activations Density 0.000%

    No Known Activations