© 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. 65981
    Prev
    Next
    INDEX
    Explanations

    interface declarations

    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
     několika
    -1.86
    şk
    -1.75
     dwóch
    -1.71
     lidé
    -1.67
     dritte
    -1.67
     gancho
    -1.60
    crema
    -1.59
     několik
    -1.58
     OGSÅ
    -1.56
     milhares
    -1.55
    POSITIVE LOGITS
    d
    2.02
     are
    1.95
     It
    1.81
    5
    1.78
     Also
    1.74
    mann
    1.72
    it
    1.69
    Продам
    1.67
    t
    1.67
    !”
    1.66
    Activations Density 0.006%

    No Known Activations