© 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. 22-GEMMASCOPE-RES-131K
    7. 39376
    Prev
    Next
    INDEX
    Explanations

    Donovan, Arizona, Diamond, Lasso

    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_22/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
     as
    -1.31
     evidently
    -1.21
     appropriately
    -1.19
     considerably
    -1.18
     breve
    -1.14
     unequivocally
    -1.13
     swiftly
    -1.13
     While
    -1.13
    Despite
    -1.09
     through
    -1.08
    POSITIVE LOGITS
    ᠌
    1.38
     comprando
    1.28
     utilizó
    1.26
     DÍA
    1.23
     HISTORIA
    1.23
     hébergement
    1.20
     savons
    1.18
     heeft
    1.16
     kompak
    1.14
     congrès
    1.13
    Activations Density 0.121%

    No Known Activations