© 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. 105156
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence endings

    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
    ఽ
    -2.41
    ︲
    -2.34
    呖
    -2.22
    鵙
    -2.11
    ኗ
    -2.08
    圌
    -2.02
     charming
    -1.99
     renowned
    -1.99
     zoude
    -1.95
     wist
    -1.88
    POSITIVE LOGITS
    ’
    2.86
     with
    2.30
     an
    2.20
     While
    2.16
     and
    2.14
     in
    2.14
     Since
    2.09
     Only
    2.06
     ONLY
    2.05
     There
    1.98
    Activations Density 0.086%

    No Known Activations