© 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. 13066
    Prev
    Next
    INDEX
    Explanations

    code structure definitions

    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
     rabat
    -2.16
     apporter
    -2.13
    них
    -2.09
    isesta
    -2.09
    Etimología
    -2.08
     juſ
    -2.08
    quelles
    -2.08
     vérifier
    -2.05
     odkazy
    -2.03
     visuel
    -2.03
    POSITIVE LOGITS
    {
    3.19
    ↵↵
    2.83
     was
    2.66
     can
    2.64
     will
    2.47
     in
    2.39
     has
    2.30
    ’
    2.19
     should
    2.19
    It
    2.03
    Activations Density 0.348%

    No Known Activations