© 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. 174321
    Prev
    Next
    INDEX
    Explanations

    detailedassessmentgroupembarrassing

    np_acts-logits-general · gemini-2.5-flash-lite

    calculation and fantasy genres

    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
    Bren
    0.49
    скі
    0.48
    Aly
    0.47
    гідно
    0.47
     outline
    0.46
    ifying
    0.45
    د
    0.45
     outlining
    0.44
    л
    0.44
    Ба
    0.44
    POSITIVE LOGITS
     komme
    0.55
     温度
    0.54
     Egipto
    0.51
     která
    0.49
     ល
    0.49
    LLCATS
    0.48
     வடி
    0.48
     政
    0.48
     Surv
    0.47
     壁
    0.47
    Activations Density 0.000%

    No Known Activations