© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79329
    Prev
    Next
    INDEX
    Explanations

    educational, analytical, ethical, and legal disclaimers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ients
    0.51
    وسي
    0.47
    Р
    0.46
    สิ่งที่
    0.45
     і
    0.45
     isn
    0.45
    시
    0.45
     시
    0.44
     that
    0.44
     postulates
    0.43
    POSITIVE LOGITS
     beque
    0.47
     médicos
    0.46
    अंग्रे
    0.46
    رشف
    0.44
     cuadrados
    0.42
     خدنا
    0.40
    Arabic
    0.40
     registrados
    0.40
    บน
    0.39
     जलाश
    0.39
    Activations Density 0.011%

    No Known Activations