© 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. 62092
    Prev
    Next
    INDEX
    Explanations

    business and organizations

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

    non-english words and symbols

    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
    請
    0.43
     thema
    0.42
    是因為
    0.42
     earlier
    0.40
    ച്ചത്
    0.39
     امرأة
    0.39
     expression
    0.38
    "(
    0.38
     decidido
    0.38
     replying
    0.38
    POSITIVE LOGITS
     تے
    0.44
     erweit
    0.43
    ൺലൈ
    0.42
     $+$
    0.40
     வள
    0.40
    Strateg
    0.39
    תיים
    0.39
    Innen
    0.39
     dział
    0.39
    ുടെ
    0.38
    Activations Density 0.015%

    No Known Activations