© 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. 143092
    Prev
    Next
    INDEX
    Explanations

    faith or law

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

    borrowing at a fixed rate

    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
    线上
    0.41
     मतलब
    0.41
    대
    0.41
    眼前
    0.39
    THING
    0.39
    ບໍ່
    0.39
    度和
    0.39
    τούν
    0.38
    桌面
    0.38
    节省
    0.38
    POSITIVE LOGITS
    fait
    0.55
    nell
    0.50
    jata
    0.50
     進
    0.47
    ित्र
    0.46
     Bik
    0.46
     mmf
    0.46
    cciona
    0.45
     your
    0.45
    nst
    0.45
    Activations Density 0.000%

    No Known Activations