© 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. 165752
    Prev
    Next
    INDEX
    Explanations

    percent rise

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

    outline creation

    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
    venue
    0.49
    <0x8A>
    0.48
     ನ್ಯಾಯ
    0.48
     そんな
    0.47
    istisch
    0.46
     ሰው
    0.46
     सॉल्व
    0.46
    dance
    0.45
     사이즈
    0.45
     নৃত
    0.45
    POSITIVE LOGITS
     rac
    0.46
     imparting
    0.43
     =
    0.43
     racers
    0.43
    ΝΑ
    0.42
     vulnerabilities
    0.42
     categories
    0.42
    再生
    0.42
     regener
    0.41
    나가
    0.41
    Activations Density 0.000%

    No Known Activations