© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71441
    Prev
    Next
    INDEX
    Explanations

    mild descriptor of a state or condition

    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
    ↵
    -3.69
     ‘‘
    -3.13
     ‘’
    -2.86
     "
    -2.77
     ''
    -2.67
     ”
    -2.64
    に対して
    -2.47
     They
    -2.36
     #
    -2.28
     tienen
    -2.23
    POSITIVE LOGITS
    Ꮓ
    3.03
    s
    2.77
     аккура
    2.75
    蟶
    2.67
     墊
    2.66
    鮠
    2.63
     miliardi
    2.58
    鼷
    2.58
    镡
    2.52
    蠖
    2.47
    Activations Density 0.003%

    No Known Activations