© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 124107
    Prev
    Next
    INDEX
    Explanations

    times of difficulty

    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
    开口道
    -2.13
    隳
    -2.11
    鸸
    -1.77
    鵞
    -1.76
    hpur
    -1.74
     climático
    -1.74
     Diakses
    -1.74
    嫫
    -1.73
    憮
    -1.72
    薷
    -1.70
    POSITIVE LOGITS
    f
    2.22
    times
    1.91
    ti
    1.89
    It
    1.88
    巴黎
    1.80
    (\
    1.77
    in
    1.75
    (
    1.75
    .
    1.72
    an
    1.71
    Activations Density 0.009%

    No Known Activations