© 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-16K
    7. 8406
    Prev
    Next
    INDEX
    Explanations

    torch and cuda code

    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_16k_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
    ort
    0.45
    re
    0.43
    contract
    0.42
    ’
    0.42
    global
    0.42
    $
    0.41
    grow
    0.40
    op
    0.40
    RE
    0.39
    utions
    0.39
    POSITIVE LOGITS
    杫
    0.45
     gebo
    0.45
     granule
    0.44
    信息化
    0.44
    穵
    0.44
     lym
    0.44
    PropertyParam
    0.44
    ழுகு
    0.44
     એપ્
    0.44
     lbl
    0.43
    Activations Density 0.018%

    No Known Activations