© 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. 142865
    Prev
    Next
    INDEX
    Explanations

    customers and clients availability

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

    Mumbai

    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
    複
    0.43
    STRUCT
    0.42
    PRES
    0.41
    UB
    0.40
     વિદ્ય
    0.40
     M
    0.40
     lé
    0.37
     UBS
    0.37
     Useful
    0.36
     Pastor
    0.36
    POSITIVE LOGITS
    <unused95>
    0.41
     ಹೃದಯ
    0.40
    ekar
    0.39
    mkdir
    0.38
    шкина
    0.38
     desarrollar
    0.38
    Gotham
    0.38
     oatmeal
    0.38
    osaurus
    0.38
    啝
    0.37
    Activations Density 0.024%

    No Known Activations