© 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. 60823
    Prev
    Next
    INDEX
    Explanations

    Hayden Jerome Clooney

    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
     Даже
    -2.61
     excellently
    -2.59
     возможностей
    -2.55
    夀
    -2.48
     impressively
    -2.48
     frantically
    -2.47
     interestingly
    -2.39
    皲
    -2.30
    也就是说
    -2.23
     факторов
    -2.22
    POSITIVE LOGITS
    那时候
    2.48
    the
    2.34
    子和
    2.22
    鲩
    2.22
    拶
    2.16
    那個
    2.13
    tures
    2.09
     и
    2.09
    2.08
     Richtlinien
    2.05
    Activations Density 0.002%
    No Known Activations