© 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. 78542
    Prev
    Next
    INDEX
    Explanations

    Why matters

    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
     his
    0.61
     Ke
    0.52
    6
    0.52
     May
    0.50
     Mozart
    0.50
     mely
    0.48
     e
    0.48
     gone
    0.47
     set
    0.46
     he
    0.46
    POSITIVE LOGITS
    aków
    0.48
    kovi
    0.46
     광고
    0.46
    pieceSelection
    0.45
    Karena
    0.45
     투자
    0.44
     اہلِ
    0.44
    ዐይን
    0.44
    compressible
    0.43
    푞
    0.43
    Activations Density 0.003%

    No Known Activations