© 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. 80697
    Prev
    Next
    INDEX
    Explanations

    contact with

    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
    as
    -1.82
    .'”
    -1.77
    _
    -1.59
    now
    -1.58
    end
    -1.56
    na
    -1.54
    nd
    -1.52
    ks
    -1.50
    lit
    -1.49
     they
    -1.48
    POSITIVE LOGITS
    沨
    2.17
    おわりに
    1.95
    なりません
    1.69
    莴
    1.68
     leta
    1.67
    ᠌
    1.66
     Füßen
    1.64
     dissimilar
    1.63
    }
    1.61
     impede
    1.59
    Activations Density 0.031%

    No Known Activations