© 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. 155502
    Prev
    Next
    INDEX
    Explanations

    IA information

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

    Federal Regulation

    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
    ನ್‌
    0.57
    știg
    0.50
     உறுப்பின
    0.49
    有害
    0.49
     قوم
    0.48
     лёг
    0.47
    郗
    0.47
    酗
    0.45
    簡単な
    0.45
     सैनिकों
    0.45
    POSITIVE LOGITS
     $\
    0.54
     $|\
    0.50
     bande
    0.50
     DIE
    0.50
     barbe
    0.50
     bandas
    0.50
     opções
    0.49
     kesehatan
    0.49
     alternativas
    0.49
     alternativa
    0.48
    Activations Density 0.000%

    No Known Activations