© 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. 75595
    Prev
    Next
    INDEX
    Explanations

    names, branding, and technical terms

    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
     изобре
    0.49
     अध्यक्षता
    0.48
    {
    0.48
     algebraic
    0.46
    बी
    0.46
     автомобиля
    0.46
     inhaled
    0.43
     премии
    0.43
     උ
    0.43
     ajax
    0.42
    POSITIVE LOGITS
    2
    0.53
     Mathis
    0.51
     Dup
    0.49
     Mel
    0.49
     Forte
    0.48
    cald
    0.47
    燦
    0.47
     Shekhar
    0.46
     চট্ট
    0.45
    關注
    0.45
    Activations Density 0.001%

    No Known Activations