© 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. 10790
    Prev
    Next
    INDEX
    Explanations

    this followed by a specific item

    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
     白い
    -1.91
     kedi
    -1.86
     kartun
    -1.75
     komik
    -1.73
    時候
    -1.72
     carré
    -1.68
    蚍
    -1.67
     dekoratif
    -1.66
     protokol
    -1.63
     aussit
    -1.63
    POSITIVE LOGITS
     to
    3.30
     for
    2.66
     in
    2.52
     with
    2.05
     is
    2.02
     from
    2.02
     during
    1.98
     without
    1.97
     as
    1.94
     information
    1.85
    Activations Density 0.046%

    No Known Activations