© 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. 222928
    Prev
    Next
    INDEX
    Explanations

    payment and transactions

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

    power imbalance and reaction

    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
     fréquentes
    0.48
    Present
    0.45
    蒎
    0.44
    你自己
    0.44
     vég
    0.43
    舴
    0.43
     রূপে
    0.43
    वारीत
    0.43
     haszn
    0.42
     modos
    0.42
    POSITIVE LOGITS
     inequality
    0.48
    IC
    0.46
     Север
    0.45
     ALL
    0.44
    ALL
    0.43
    D
    0.42
     Nations
    0.42
    U
    0.42
     nations
    0.41
    K
    0.41
    Activations Density 0.001%

    No Known Activations