© 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. 60172
    Prev
    Next
    INDEX
    Explanations

    so followed by outcome or explanation

    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
     kosme
    -1.84
     konkre
    -1.83
    Cevap
    -1.74
     排骨
    -1.73
    leyin
    -1.73
     akut
    -1.66
     reacties
    -1.66
    轱
    -1.63
    Ꮚ
    -1.62
     jaun
    -1.60
    POSITIVE LOGITS
     had
    2.05
    ol
    2.03
     as
    2.02
     with
    1.96
     won
    1.95
    }
    1.95
     didn
    1.91
     seems
    1.88
    ."
    1.88
    hline
    1.87
    Activations Density 0.006%

    No Known Activations