© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 33175
    Prev
    Next
    INDEX
    Explanations

    java class definitions and tests

    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
    z
    0.72
    is
    0.71
    le
    0.71
    oa
    0.70
    or
    0.69
    title
    0.68
    to
    0.67
    ee
    0.67
    ing
    0.67
    table
    0.66
    POSITIVE LOGITS
    ی
    0.72
    임
    0.67
    )，
    0.63
    ست
    0.60
    縛
    0.60
    ရပ်
    0.59
    ोटो
    0.59
    бу
    0.57
    ві
    0.57
    ড
    0.57
    Activations Density 0.004%

    No Known Activations