© 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. 75609
    Prev
    Next
    INDEX
    Explanations

    expressions of hate

    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
     ”
    -2.11
    ៚
    -2.03
     –
    -1.91
    dicionado
    -1.91
     ’
    -1.88
    .’’
    -1.86
    金币
    -1.86
    The
    -1.86
    嫆
    -1.80
    atação
    -1.80
    POSITIVE LOGITS
    ↵
    2.13
     tinham
    1.79
     месе
    1.78
     pasaron
    1.72
     pudieron
    1.68
     it
    1.68
    0
    1.66
    1
    1.63
     getNombre
    1.61
     habrían
    1.56
    Activations Density 0.009%

    No Known Activations