© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99810
    Prev
    Next
    INDEX
    Explanations

    noun followed by common verb

    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_34/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
     remarquable
    -1.38
     siè
    -1.32
    unno
    -1.31
     appréci
    -1.27
    occurs
    -1.23
     écout
    -1.23
     surpren
    -1.22
     héri
    -1.22
     mariée
    -1.21
     véhicule
    -1.20
    POSITIVE LOGITS
     has
    2.61
     had
    2.55
     didn
    2.44
     will
    2.17
     cannot
    2.11
     did
    2.09
     could
    2.09
     have
    2.08
     should
    2.02
     would
    1.98
    Activations Density 0.100%

    No Known Activations