© 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. 71581
    Prev
    Next
    INDEX
    Explanations

    separators and code elements

    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
     a
    -1.22
     these
    -1.14
    peka
    -0.96
     that
    -0.96
     potřeb
    -0.94
     all
    -0.94
    idase
    -0.93
     Vergnügen
    -0.93
     trasero
    -0.92
     as
    -0.91
    POSITIVE LOGITS
     BEAUTIFUL
    1.06
    }>
    0.99
    Then
    0.96
    LIGHTS
    0.94
    FINISH
    0.94
    does
    0.94
    many
    0.93
    AGUA
    0.93
    OVERN
    0.93
    MANY
    0.93
    Activations Density 0.038%

    No Known Activations