© 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. 46331
    Prev
    Next
    INDEX
    Explanations

    mpd, mtime, M1, main, move_m@

    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
    in
    0.79
    of
    0.67
    p
    0.61
    at
    0.57
    it
    0.56
    rome
    0.53
    pac
    0.53
    pall
    0.52
    н
    0.52
    ai
    0.51
    POSITIVE LOGITS
     เมตร
    0.66
     müz
    0.61
    지막
    0.59
     M
    0.59
    ână
    0.58
    ushroom
    0.57
     Muslim
    0.57
    ilitary
    0.57
     hashlib
    0.56
    endoza
    0.55
    Activations Density 0.371%

    No Known Activations