© 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. 105749
    Prev
    Next
    INDEX
    Explanations

    Q:

    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
     (
    -2.44
     even
    -2.30
     as
    -2.25
     [
    -2.00
     when
    -1.98
     so
    -1.96
     with
    -1.95
     -
    -1.95
    </em>
    -1.92
     just
    -1.91
    POSITIVE LOGITS
     delightfully
    2.17
    嫑
    2.14
    褙
    2.05
    creating
    2.05
     GETTING
    2.00
    ครื่อง
    1.99
    piej
    1.97
    怱
    1.96
    歺
    1.95
     triko
    1.95
    Activations Density 0.003%

    No Known Activations