© 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. 16-GEMMASCOPE-2-RES-262K
    7. 49029
    Prev
    Next
    INDEX
    Explanations

    testing setup helper

    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_16_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
    speople
    0.59
    zhou
    0.54
    A
    0.54
     pü
    0.51
    Collaboration
    0.50
    Ç
    0.50
    Building
    0.49
    Meeting
    0.49
    rahm
    0.49
    fah
    0.47
    POSITIVE LOGITS
    ים
    0.68
    га
    0.63
     đều
    0.62
    은
    0.56
    ട്ടി
    0.56
    鷄
    0.55
    鸡
    0.53
    끗
    0.52
     defecto
    0.52
    は
    0.52
    Activations Density 0.000%

    No Known Activations