© 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. 60700
    Prev
    Next
    INDEX
    Explanations

    Welsh: professions, places, and things

    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
    ’
    -2.63
    稣
    -2.63
    鸲
    -2.56
    i
    -2.50
    伥
    -2.48
    厛
    -2.44
    a
    -2.42
    蹀
    -2.41
    ญี่ป
    -2.39
    が付いて
    -2.39
    POSITIVE LOGITS
    lossians
    2.61
    man
    2.38
    idjan
    2.36
    When
    2.33
    derdag
    2.33
    něte
    2.25
    tissement
    2.23
    Revenir
    2.20
    ();//
    2.17
    使用
    2.16
    Activations Density 0.001%

    No Known Activations