© 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-65K
    7. 62627
    Prev
    Next
    INDEX
    Explanations

    Kitchen Spectrum

    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_65k_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
     reação
    0.45
     procesos
    0.42
    ર્ગ
    0.40
    relief
    0.40
    佥
    0.39
     arousal
    0.39
    ramento
    0.39
     поступ
    0.39
    ાર
    0.38
    рма
    0.38
    POSITIVE LOGITS
     Mobile
    0.56
     Snake
    0.50
     Montreal
    0.49
     Stone
    0.49
     無
    0.49
     Surprisingly
    0.48
     暗
    0.47
     Stell
    0.47
     لدينا
    0.47
     Old
    0.46
    Activations Density 0.003%

    No Known Activations