© 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. 14875
    Prev
    Next
    INDEX
    Explanations

    crucial step

    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
    olecules
    0.56
    懋
    0.55
    nese
    0.54
    armed
    0.51
    guru
    0.51
    녔
    0.50
    misc
    0.49
    mäß
    0.49
    eries
    0.49
    cimiento
    0.48
    POSITIVE LOGITS
     perc
    0.49
     habitat
    0.47
     hat
    0.46
     separar
    0.46
     incre
    0.46
     tax
    0.46
     ver
    0.45
     khen
    0.45
     F
    0.44
     Tax
    0.44
    Activations Density 0.003%

    No Known Activations