© 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. 48371
    Prev
    Next
    INDEX
    Explanations

    call numbers and dates

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

    standard math

    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
     भी
    0.48
     पुष्टि
    0.47
    濩
    0.46
     तु
    0.46
    <0xE8>
    0.45
    occupied
    0.45
    仍
    0.44
     विवा
    0.44
     Sosa
    0.44
    oyant
    0.43
    POSITIVE LOGITS
            
    0.46
     môžete
    0.46
             
    0.45
     дерева
    0.45
     jednotliv
    0.45
    ដែលអាច
    0.44
     aplatis
    0.44
    Inline
    0.44
     convexes
    0.43
     problemler
    0.43
    Activations Density 0.000%

    No Known Activations