© 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. 198034
    Prev
    Next
    INDEX
    Explanations

    lawmakers, modern evolution, legal ownership

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

    established API, simply win

    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
    張
    0.49
     apartments
    0.48
    ুন
    0.45
     bonds
    0.44
     originating
    0.44
    さて
    0.44
     pavements
    0.44
    年に
    0.43
     rapides
    0.43
    極
    0.43
    POSITIVE LOGITS
     интернете
    0.48
     сын
    0.48
    leukin
    0.47
    
    0.46
    লেখা
    0.46
    DebuggingMode
    0.44
     setSnackbar
    0.44
    referer
    0.43
    莼
    0.43
     Потом
    0.42
    Activations Density 0.000%

    No Known Activations