© 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. 48341
    Prev
    Next
    INDEX
    Explanations

    sports and media topics

    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
     of
    -1.45
     his
    -1.38
     лишь
    -1.38
     belge
    -1.37
     Küchen
    -1.36
     rasch
    -1.34
     ordinaire
    -1.34
    怼
    -1.34
    —¡
    -1.32
     a
    -1.30
    POSITIVE LOGITS
     there
    2.53
     we
    2.31
     that
    2.00
     you
    1.98
     it
    1.85
    も行
    1.81
     It
    1.77
    なども
    1.73
     they
    1.68
    や
    1.68
    Activations Density 0.056%

    No Known Activations