© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 5372
    Prev
    Next
    INDEX
    Explanations

    ThisWorkbook

    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
    صدر
    0.46
    윤
    0.43
    سم
    0.40
    ಿಸುತ್ತದೆ
    0.39
    尹
    0.38
    㪯
    0.38
    っております
    0.37
     అనేది
    0.37
    䇞
    0.36
    埛
    0.36
    POSITIVE LOGITS
     und
    0.41
     delays
    0.41
    engers
    0.40
     flaws
    0.40
    uses
    0.40
    delay
    0.40
    inos
    0.39
    week
    0.39
    und
    0.39
    close
    0.39
    Activations Density 0.001%

    No Known Activations