© 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. 65193
    Prev
    Next
    INDEX
    Explanations

    to those

    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
     it
    -2.88
     that
    -2.42
     the
    -1.97
     or
    -1.80
     each
    -1.70
     perhaps
    -1.70
     seems
    -1.66
     this
    -1.59
     for
    -1.58
     as
    -1.56
    POSITIVE LOGITS
    useNewUrlParser
    1.95
    Ᏹ
    1.80
    everyone
    1.74
    EVERY
    1.73
     ideje
    1.68
    νονται
    1.63
    Inhalte
    1.61
     tých
    1.60
    ebles
    1.58
    those
    1.57
    Activations Density 0.235%

    No Known Activations