© 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. 41-GEMMASCOPE-2-RES-262K
    7. 25911
    Prev
    Next
    INDEX
    Explanations

    GLSL vec and uniforms

    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_all/layer_41_width_262k_l0_big
    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
     spends
    0.38
    甠
    0.38
    மா
    0.37
    涳
    0.37
    rover
    0.37
    istor
    0.37
    ோட
    0.37
     excelencia
    0.36
    岸
    0.36
    machine
    0.36
    POSITIVE LOGITS
     vec
    0.96
    vec
    0.77
     Vec
    0.61
    Vec
    0.55
     glm
    0.49
    glm
    0.48
     fract
    0.45
     ве
    0.44
     mix
    0.44
     Mix
    0.43
    Activations Density 0.004%

    No Known Activations