© 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. 47982
    Prev
    Next
    INDEX
    Explanations

    link to or of

    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
    ↵
    -1.66
     mè
    -1.64
     этого
    -1.64
     gewi
    -1.61
     ort
    -1.56
     dring
    -1.56
     rác
    -1.56
     they
    -1.55
    ;.
    -1.54
     sors
    -1.52
    POSITIVE LOGITS
     all
    1.66
     belligerent
    1.61
     undeniably
    1.60
     or
    1.56
     supremely
    1.55
     took
    1.52
     Though
    1.52
     gave
    1.51
     to
    1.50
     also
    1.50
    Activations Density 0.409%

    No Known Activations