© 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. 21504
    Prev
    Next
    INDEX
    Explanations

    also known as / or

    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
    쾌
    0.39
    儼
    0.38
    ണു
    0.37
    ሆኑ
    0.36
     vouloir
    0.35
    牖
    0.34
     unmistak
    0.34
    可谓
    0.34
    ۆی
    0.34
    {[\
    0.34
    POSITIVE LOGITS
    also
    0.47
     или
    0.46
     also
    0.46
     alebo
    0.46
    as
    0.45
     లేదా
    0.44
    actoring
    0.43
     or
    0.43
     किंवा
    0.41
    aka
    0.41
    Activations Density 0.115%

    No Known Activations