© 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. 33287
    Prev
    Next
    INDEX
    Explanations

    look into

    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
    шения
    0.68
    sembles
    0.68
    朹
    0.65
    kennt
    0.64
    ！)
    0.64
    ensibly
    0.63
    杝
    0.63
    acios
    0.62
     Listening
    0.62
    лган
    0.62
    POSITIVE LOGITS
    H
    1.49
    A
    1.46
    א
    1.36
    U
    1.33
    C
    1.32
    B
    1.31
    Q
    1.29
    M
    1.27
    W
    1.24
    Z
    1.24
    Activations Density 0.001%

    No Known Activations