© 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. 29150
    Prev
    Next
    INDEX
    Explanations

    easel, Lent, Easter, egg, vases

    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
    1
    1.66
    5
    1.20
    3
    1.15
    4
    1.08
    ک
    0.97
    ed
    0.93
    o
    0.82
    ol
    0.81
    B
    0.80
    to
    0.80
    POSITIVE LOGITS
    ，
    0.88
    助于
    0.78
     tám
    0.74
     belieb
    0.74
    MathMarks
    0.71
    有望
    0.70
     اك
    0.69
    ан
    0.69
    ،
    0.69
     كيلو
    0.68
    Activations Density 0.001%

    No Known Activations