© 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. 50961
    Prev
    Next
    INDEX
    Explanations

    concepts, transactions, and computing

    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
    pInBuffer
    0.57
     striées
    0.54
    Ϣ
    0.48
    舝
    0.45
     sAlarm
    0.44
     Caedwalla
    0.42
    ",[],"
    0.42
    ueel
    0.41
     확인할
    0.41
    頩
    0.41
    POSITIVE LOGITS
    uit
    0.46
    begin
    0.44
    يل
    0.44
    وني
    0.44
     radiative
    0.44
    après
    0.44
     finance
    0.43
     telescope
    0.42
    価格
    0.42
    U
    0.42
    Activations Density 0.014%

    No Known Activations