© 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. 10-GEMMASCOPE-RES-131K
    7. 19026
    Prev
    Next
    INDEX
    Explanations

    examining with care

    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
     fera
    -1.38
    遢
    -1.37
     magnifique
    -1.37
     excellente
    -1.36
     sauve
    -1.34
     passé
    -1.33
    小声
    -1.32
     grands
    -1.32
     faire
    -1.31
    пите
    -1.30
    POSITIVE LOGITS
     how
    2.09
     what
    1.95
     to
    1.87
     which
    1.81
     that
    1.79
     those
    1.77
     will
    1.65
     the
    1.64
     who
    1.57
     where
    1.50
    Activations Density 0.015%

    No Known Activations