© 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. 105920
    Prev
    Next
    INDEX
    Explanations

    Segunda División, Primera División

    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
    鐽
    -2.84
    蚱
    -2.73
    歘
    -2.69
    legte
    -2.67
    镦
    -2.64
    料
    -2.61
    🧌
    -2.59
    茕
    -2.56
     แต่
    -2.53
    癰
    -2.53
    POSITIVE LOGITS
    The
    3.84
    This
    3.84
    In
    3.41
    1
    3.34
    However
    3.27
     begle
    3.17
    It
    3.14
    What
    3.09
    Since
    3.09
    While
    3.06
    Activations Density 0.002%

    No Known Activations