© 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. 90223
    Prev
    Next
    INDEX
    Explanations

    parts of systems or objects

    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
    ного
    0.54
     Jefe
    0.52
    的总
    0.52
    ным
    0.51
    lementine
    0.50
    _
    0.50
    Supreme
    0.48
    ى
    0.48
    ست
    0.47
     умолчанию
    0.47
    POSITIVE LOGITS
     aval
    0.56
     afar
    0.56
    ❆
    0.55
    ９
    0.54
     fibers
    0.54
     ゴ
    0.53
     pioneered
    0.53
     airlift
    0.53
     areas
    0.53
     adapt
    0.53
    Activations Density 0.000%

    No Known Activations