© 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. 12331
    Prev
    Next
    INDEX
    Explanations

    measured quantity or state

    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
     molti
    -1.59
     magnific
    -1.58
     masterful
    -1.56
     seront
    -1.53
     alcune
    -1.52
     constater
    -1.49
     siè
    -1.49
     are
    -1.48
     horrid
    -1.48
    primarily
    -1.47
    POSITIVE LOGITS
     which
    2.14
     their
    2.09
     your
    1.94
     the
    1.93
     if
    1.90
     for
    1.77
     at
    1.70
     regardless
    1.70
     required
    1.70
     any
    1.66
    Activations Density 0.197%

    No Known Activations