© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1555
    Prev
    Next
    INDEX
    Explanations

    many followed by a category

    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_31_width_16k_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
    ’
    0.39
    ak
    0.38
    ac
    0.35
    iling
    0.35
    ome
    0.35
    ump
    0.34
     it
    0.33
    lon
    0.33
    isés
    0.32
    ysis
    0.31
    POSITIVE LOGITS
     dintre
    0.39
    -
    0.36
     (>
    0.36
    кратно
    0.34
     людей
    0.33
    ではない
    0.33
     centaines
    0.33
    تها
    0.32
     частина
    0.31
    ுற
    0.31
    Activations Density 0.195%

    No Known Activations