© 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. 40-GEMMASCOPE-2-RES-262K
    7. 136096
    Prev
    Next
    INDEX
    Explanations

    options, lists, ranges

    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_40_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
    уро
    0.38
     सिक्योरिटी
    0.38
    ܸ
    0.38
    मक
    0.37
    ĩa
    0.37
    aceutical
    0.36
    rech
    0.36
    ikai
    0.36
     реє
    0.36
    теро
    0.36
    POSITIVE LOGITS
     shovel
    0.37
     Dot
    0.37
     meines
    0.37
     fus
    0.36
    |}{
    0.35
    成长
    0.35
     الخلا
    0.35
     Lehenga
    0.35
     Af
    0.35
    ashboard
    0.35
    Activations Density 0.004%

    No Known Activations