© 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. 71180
    Prev
    Next
    INDEX
    Explanations

    further study needed

    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
     dám
    -1.65
     rév
    -1.48
     réal
    -1.47
     quelcon
    -1.43
     humanas
    -1.43
     bén
    -1.42
     quelquefois
    -1.41
     två
    -1.41
    sighs
    -1.41
     rése
    -1.39
    POSITIVE LOGITS
     this
    1.97
     each
    1.85
     how
    1.68
     to
    1.67
     what
    1.65
    他
    1.63
     more
    1.62
     here
    1.58
     such
    1.52
     it
    1.50
    Activations Density 0.068%

    No Known Activations