© 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. 8596
    Prev
    Next
    INDEX
    Explanations

    big topic, part, change, component, shock, plus

    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
    "./
    -1.52
    The
    -1.46
     have
    -1.43
    ᕱ
    -1.42
    “
    -1.42
    طن
    -1.41
     festgestellt
    -1.40
     cadeiras
    -1.38
    使用
    -1.37
    時
    -1.36
    POSITIVE LOGITS
    <bos>
    1.57
     perceptive
    1.54
     czerwca
    1.48
    勿論
    1.45
    后来
    1.40
    重要な
    1.40
     homoto
    1.38
    だけでなく
    1.35
     fű
    1.34
     DLA
    1.34
    Activations Density 0.023%

    No Known Activations