© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 150864
    Prev
    Next
    INDEX
    Explanations

    apartment catering piece life

    np_acts-logits-general · gemini-2.5-flash-lite

    explain or redefine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     スタ
    0.49
    且
    0.47
    istatic
    0.45
     č
    0.45
    iaz
    0.44
    ଝ
    0.44
    👪
    0.44
    idez
    0.44
    serde
    0.43
    シス
    0.43
    POSITIVE LOGITS
     réflex
    0.46
    resTmp
    0.44
     अलै
    0.39
    告诉你
    0.39
    ሏ
    0.38
    劧
    0.38
    ใต้
    0.38
    Anything
    0.38
     దక్షి
    0.38
    <unused2156>
    0.38
    Activations Density 0.005%

    No Known Activations