© 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. 90671
    Prev
    Next
    INDEX
    Explanations

    materials provided

    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
    y
    -2.86
    岀
    -2.83
    êts
    -2.77
    ligators
    -2.73
    derdag
    -2.64
    ésil
    -2.64
    樒
    -2.64
    linawan
    -2.52
    yā
    -2.47
    ipeline
    -2.44
    POSITIVE LOGITS
    In
    3.41
    However
    2.52
    </u>
    2.48
    –
    2.45
    なかなか
    2.38
    You
    2.31
    5
    2.31
     десять
    2.30
    Initially
    2.28
    ...
    2.25
    Activations Density 0.012%

    No Known Activations