© 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. 78568
    Prev
    Next
    INDEX
    Explanations

    increased gun

    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
    을
    0.53
     ಮೆ
    0.47
     Timurtaş
    0.47
     Запад
    0.46
     참
    0.45
     menerima
    0.44
     запа
    0.44
     डायब
    0.44
     미국의
    0.44
    ﮕ
    0.43
    POSITIVE LOGITS
    1
    0.50
    يز
    0.50
    7
    0.47
    site
    0.46
    delay
    0.46
     curved
    0.46
    ьо
    0.46
    宽
    0.46
     amén
    0.45
    ر
    0.45
    Activations Density 0.001%

    No Known Activations