© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 134804
    Prev
    Next
    INDEX
    Explanations

    lists, pts, listing, bugs, Queue, astore

    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_40_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
    ক্ষার
    0.48
    listItem
    0.46
    alignParentRight
    0.44
    southeast
    0.44
    ूबर
    0.43
    resultlist
    0.43
     obič
    0.42
    <unused636>
    0.42
    offsetof
    0.41
    neigh
    0.41
    POSITIVE LOGITS
     Discover
    0.47
     Loksatta
    0.45
     L
    0.42
     Certificate
    0.41
    ヮ
    0.40
     mas
    0.39
     Pal
    0.39
     O
    0.39
     pos
    0.39
     Biological
    0.39
    Activations Density 0.001%

    No Known Activations