© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 31201
    Prev
    Next
    INDEX
    Explanations

    Wan Hu, Papyrus, activity, relationships

    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
     an
    1.16
     at
    0.93
    ल
    0.88
    os
    0.85
    et
    0.85
    iferous
    0.84
     in
    0.83
     on
    0.82
    vention
    0.82
    ро
    0.81
    POSITIVE LOGITS
    t
    1.16
    y
    1.16
    p
    1.14
    g
    1.13
    ع
    1.05
    was
    0.94
    to
    0.94
    ار
    0.93
     getActivity
    0.90
    W
    0.89
    Activations Density 0.000%

    No Known Activations