© 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. 144719
    Prev
    Next
    INDEX
    Explanations

    rhythm playing

    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
    their
    0.61
    hours
    0.59
    There
    0.59
    t
    0.58
    When
    0.54
    import
    0.52
    pure
    0.52
    double
    0.51
    two
    0.50
    other
    0.50
    POSITIVE LOGITS
     Saúde
    0.61
    美好
    0.59
     Alguns
    0.57
    ابر
    0.55
     周
    0.55
    áticos
    0.54
    区块
    0.54
     Objetivo
    0.54
    ⾏
    0.54
     Turismo
    0.53
    Activations Density 0.000%

    No Known Activations