© 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. 211176
    Prev
    Next
    INDEX
    Explanations

    jurisdiction standards require pay

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

    phrases, concepts, or lists

    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
    googleapis
    0.35
    塡
    0.34
     («
    0.33
    ,$$
    0.33
    <unused62>
    0.32
     lucro
    0.31
     ${\
    0.31
     어떻
    0.31
     customPlot
    0.31
    <unused60>
    0.30
    POSITIVE LOGITS
     सेकंड
    0.40
     Yoruba
    0.38
     Haitian
    0.38
     dejado
    0.37
    నుక
    0.37
     सप्ताह
    0.36
     artık
    0.36
    綀
    0.36
    ）・
    0.36
    आधी
    0.36
    Activations Density 0.002%

    No Known Activations