© 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. 42009
    Prev
    Next
    INDEX
    Explanations

    back to

    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
    蚨
    -1.91
     The
    -1.87
    罽
    -1.79
    \
    -1.77
     megfelelő
    -1.63
    4
    -1.63
    felpa
    -1.63
     polegadas
    -1.63
     zijne
    -1.60
    
    -1.59
    POSITIVE LOGITS
    ).-
    1.72
    元的
    1.67
    以前
    1.61
    ､
    1.52
    ？』
    1.52
     esclusivamente
    1.48
    店
    1.45
    匐
    1.45
     мамы
    1.44
    她
    1.44
    Activations Density 0.009%

    No Known Activations