© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26585
    Prev
    Next
    INDEX
    Explanations

    noun followed by noun

    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_22/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
     to
    -1.05
     alanı
    -0.96
    了一些
    -0.92
    市的
    -0.92
     Ländern
    -0.89
    itude
    -0.88
     unwit
    -0.88
     offiziellen
    -0.85
     rasc
    -0.85
    去看
    -0.85
    POSITIVE LOGITS
    我们的
    1.27
    我们
    1.22
    我們
    1.05
     enfants
    1.02
     moldes
    1.01
     csomag
    0.99
     soms
    0.98
    omoto
    0.98
    ΤΟ
    0.98
     我们
    0.97
    Activations Density 0.301%

    No Known Activations