© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 47464
    Prev
    Next
    INDEX
    Explanations

    regular expression syntax

    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
     only
    -2.23
     people
    -2.11
     even
    -2.09
     of
    -1.99
     this
    -1.96
     because
    -1.84
     where
    -1.83
     our
    -1.81
     how
    -1.81
     three
    -1.80
    POSITIVE LOGITS
     poë
    1.77
    ophiles
    1.75
     plafon
    1.74
    URIDAD
    1.73
     Redacción
    1.70
     nettoy
    1.69
     fidé
    1.68
    ――――
    1.67
    ___________
    1.64
    蹓
    1.63
    Activations Density 0.036%

    No Known Activations