© 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. 69557
    Prev
    Next
    INDEX
    Explanations

    subjects followed by verbs

    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
     When
    -1.55
     our
    -1.48
     During
    -1.45
    When
    -1.34
    During
    -1.25
     JUST
    -1.24
     this
    -1.19
     because
    -1.17
     on
    -1.16
     häufig
    -1.16
    POSITIVE LOGITS
     siè
    1.38
    despite
    1.34
     hunne
    1.30
    cannot
    1.28
     inond
    1.27
     hés
    1.25
    ępu
    1.25
     geha
    1.23
     zwi
    1.23
    橚
    1.22
    Activations Density 0.133%

    No Known Activations