© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42987
    Prev
    Next
    INDEX
    Explanations

    total followed by quantity or measurement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    这个
    -1.65
    它
    -1.63
    ႐
    -1.45
     noiembrie
    -1.43
    <
    -1.43
     относительно
    -1.41
    [
    -1.41
    лем
    -1.38
     doesn
    -1.37
    枼
    -1.36
    POSITIVE LOGITS
    ご連絡
    1.74
    呖
    1.74
    一方で
    1.65
    Beskrivning
    1.64
    𐐪
    1.62
    余談
    1.60
    いかがでしたか
    1.60
     the
    1.59
    疲労
    1.58
    代わり
    1.55
    Activations Density 0.034%

    No Known Activations