© 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. 204744
    Prev
    Next
    INDEX
    Explanations

    labor market, cyber espionage, help purchase

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

    Piranesi, intelligence, development, craftsmanship

    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
    ารา
    0.55
     المال
    0.47
     লাগানো
    0.46
     ngọt
    0.44
     ครอง
    0.44
     యా
    0.43
     rivalry
    0.42
    좔
    0.42
     വഴ
    0.42
    टान
    0.42
    POSITIVE LOGITS
     brasil
    0.52
    П
    0.50
    ，
    0.48
     guter
    0.47
     fabb
    0.47
     interess
    0.46
     поддержи
    0.46
    ش
    0.46
    ୟ
    0.45
    。
    0.45
    Activations Density 0.000%

    No Known Activations