© 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. 69788
    Prev
    Next
    INDEX
    Explanations

    common phrases and prepositions

    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
     acuario
    -2.17
     revés
    -1.97
     précédemment
    -1.88
     unicornio
    -1.85
     уди
    -1.84
    栊
    -1.84
    
    -1.83
     cinturón
    -1.81
     bordado
    -1.80
    我們
    -1.79
    POSITIVE LOGITS
     in
    2.75
     to
    2.63
     also
    2.52
     any
    2.28
    in
    2.27
     their
    2.20
    !!!!
    2.13
    as
    2.09
     even
    2.09
    !!
    2.06
    Activations Density 0.004%

    No Known Activations