© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 9820
    Prev
    Next
    INDEX
    Explanations

    Q: marks questions

    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
     in
    -1.91
     only
    -1.90
     many
    -1.85
     most
    -1.84
     also
    -1.81
     other
    -1.80
     all
    -1.70
     numerous
    -1.68
     actually
    -1.66
     almost
    -1.63
    POSITIVE LOGITS
    €“
    1.95
     rembour
    1.91
     valentín
    1.70
     nôtre
    1.69
     italiens
    1.69
     jaunes
    1.67
     hés
    1.66
     peluche
    1.65
    €”
    1.64
     siè
    1.62
    Activations Density 0.000%

    No Known Activations