© 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. 145089
    Prev
    Next
    INDEX
    Explanations

    wavelength, suggested serving, Middle School

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

    parentheses containing numbers or identifiers

    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
     製
    0.48
    いずれ
    0.45
    Controlled
    0.45
    Integer
    0.44
    Incorpor
    0.43
    bouw
    0.43
     Quan
    0.42
    Entered
    0.41
    *
    0.41
    Zen
    0.40
    POSITIVE LOGITS
     regula
    0.47
    ススメ
    0.46
     δεύτε
    0.42
    飲む
    0.42
     convexity
    0.41
    ಂಡ
    0.40
     delimiters
    0.39
    ätzung
    0.39
    ာ
    0.39
     curvature
    0.38
    Activations Density 0.000%

    No Known Activations