© 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. 42230
    Prev
    Next
    INDEX
    Explanations

    programming and learning concepts

    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
    ,
    -1.63
     that
    -1.59
     which
    -1.45
    ॉन
    -1.44
    でしたか
    -1.33
     who
    -1.32
     to
    -1.31
    咴
    -1.27
    ''',
    -1.24
     británica
    -1.24
    POSITIVE LOGITS
     verstor
    1.29
    1
    1.23
     gustado
    1.23
     сожалению
    1.22
    čuje
    1.19
     nắng
    1.16
     triliun
    1.16
     espé
    1.16
     régl
    1.15
    Отзывы
    1.14
    Activations Density 0.205%

    No Known Activations