© 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. 98640
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    simplified compliance

    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
    에서의
    0.50
     avoidable
    0.46
    での
    0.44
    와의
    0.43
     मेगा
    0.42
    floxacin
    0.42
    が
    0.41
     trong
    0.40
    zantine
    0.40
    šk
    0.40
    POSITIVE LOGITS
     trabal
    0.50
    恫
    0.48
     تمر
    0.45
     Сы
    0.45
     выска
    0.45
     Syed
    0.44
    د
    0.44
     выра
    0.43
     اند
    0.43
     преми
    0.43
    Activations Density 0.000%

    No Known Activations