© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68219
    Prev
    Next
    INDEX
    Explanations

    general classification

    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
     allerlei
    -1.81
     ſever
    -1.79
    
    -1.78
     embalaje
    -1.77
     móveis
    -1.73
     drenaje
    -1.73
     praktische
    -1.68
     fabricación
    -1.66
    搋
    -1.66
     în
    -1.63
    POSITIVE LOGITS
     without
    1.66
    ),
    1.66
    </i>
    1.63
     uses
    1.58
     through
    1.58
     people
    1.54
     usually
    1.53
     will
    1.51
     comparable
    1.48
    y
    1.48
    Activations Density 0.006%

    No Known Activations