© 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. 1440
    Prev
    Next
    INDEX
    Explanations

    town hall, politics, government

    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
    咴
    -2.38
    ACIÓN
    -2.02
    鹟
    -1.96
    乆
    -1.91
    which
    -1.88
    甃
    -1.88
    拶
    -1.88
    颙
    -1.83
    𞤢
    -1.78
     ambayo
    -1.76
    POSITIVE LOGITS
    I
    2.09
     we
    1.99
    низу
    1.95
    al
    1.92
    am
    1.84
    ';
    1.73
     accustomed
    1.72
    l
    1.72
     Its
    1.70
    enablog
    1.70
    Activations Density 0.021%

    No Known Activations