© 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. 62803
    Prev
    Next
    INDEX
    Explanations

    modern, time, play, options, Manchester

    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
     Git
    0.40
     bytecode
    0.40
     UI
    0.39
    儲
    0.39
     Simple
    0.39
     UIText
    0.38
     user
    0.38
     simply
    0.38
     BC
    0.38
     Lotus
    0.38
    POSITIVE LOGITS
     ardından
    0.53
    Setelah
    0.48
    віду
    0.48
    honneur
    0.46
    ೪
    0.46
     porcentaje
    0.46
    после
    0.46
    ру
    0.45
    ாகு
    0.44
     זמן
    0.44
    Activations Density 0.001%

    No Known Activations