© 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. 36229
    Prev
    Next
    INDEX
    Explanations

    variable or constant declaration

    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
     from
    -1.30
     which
    -1.20
     at
    -1.20
     with
    -1.14
     or
    -1.13
     possibly
    -1.05
     without
    -1.04
     ogni
    -1.03
     should
    -1.02
     before
    -0.98
    POSITIVE LOGITS
     religieux
    1.23
     énergé
    1.21
    小声
    1.19
     remé
    1.18
     ridiculously
    1.18
     spéciaux
    1.17
     religieuses
    1.16
     quintessential
    1.13
     goû
    1.13
     Einladung
    1.13
    Activations Density 0.022%

    No Known Activations