© 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. 243191
    Prev
    Next
    INDEX
    Explanations

    impacts movement

    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
     сал
    0.45
     наблюдения
    0.45
    葢
    0.43
     নাস
    0.43
     шеран
    0.43
     ناس
    0.43
    ོང་
    0.43
     झाले
    0.42
    逭
    0.42
     никто
    0.41
    POSITIVE LOGITS
     vrijed
    0.53
    レ
    0.51
    르
    0.51
    ಮಾಣ
    0.50
     resonate
    0.50
     gelir
    0.49
    mj
    0.48
     zemlje
    0.47
     resonates
    0.46
     poets
    0.46
    Activations Density 0.000%

    No Known Activations