© 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. 8052
    Prev
    Next
    INDEX
    Explanations

    numbers after words

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

    list formatting markers

    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
     између
    0.36
    նել
    0.35
    CurrentByte
    0.32
    ูน
    0.32
     น้ํา
    0.31
     ስለዚህ
    0.31
    <0x1D>
    0.31
    ผ้า
    0.31
    ColorBit
    0.31
    SubDirectoryPath
    0.31
    POSITIVE LOGITS
    0.54
     published
    0.38
     websites
    0.37
     first
    0.36
     forums
    0.36
     sites
    0.34
     the
    0.33
     for
    0.33
     forum
    0.32
    <strong>
    0.32
    Activations Density 0.185%

    No Known Activations