© 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. 36446
    Prev
    Next
    INDEX
    Explanations

    small features or structures

    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
     after
    -1.71
     during
    -1.52
     before
    -1.51
     then
    -1.38
     or
    -1.37
     by
    -1.34
     most
    -1.32
     despite
    -1.30
     using
    -1.30
     epitom
    -1.30
    POSITIVE LOGITS
    一个个
    1.70
     piccoli
    1.55
     verdaderas
    1.47
     antiguas
    1.46
     reuniones
    1.41
     leſs
    1.39
     chré
    1.38
     pequeñas
    1.38
     különböző
    1.38
     téléchargement
    1.37
    Activations Density 0.126%

    No Known Activations