© 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. 41670
    Prev
    Next
    INDEX
    Explanations

    http:// or // or file

    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
     continual
    -1.73
     was
    -1.66
     has
    -1.59
     keeps
    -1.54
     furthering
    -1.49
     using
    -1.48
     officiers
    -1.48
     keep
    -1.48
     took
    -1.42
     baile
    -1.41
    POSITIVE LOGITS
     diversos
    2.02
    ⁛
    1.77
     unbelievably
    1.77
    傒
    1.74
     magnificent
    1.73
    そんなに
    1.66
     superb
    1.65
     magnific
    1.63
     goofy
    1.62
     strikingly
    1.59
    Activations Density 0.000%

    No Known Activations