© 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. 61773
    Prev
    Next
    INDEX
    Explanations

    spoken a

    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
     ワ
    0.60
     インド
    0.55
     перспекти
    0.53
     wypad
    0.50
     wholeheartedly
    0.49
     earnestly
    0.49
     ფუნქ
    0.48
    peror
    0.47
    velles
    0.47
     შეიძლება
    0.47
    POSITIVE LOGITS
    한
    0.48
    ρή
    0.46
     trò
    0.45
    "
    0.45
    挂
    0.44
     tutto
    0.44
    τής
    0.42
     todo
    0.41
     portion
    0.41
    0.41
    Activations Density 0.029%

    No Known Activations