© 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. 8450
    Prev
    Next
    INDEX
    Explanations

    geocoding addresses and markers

    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
    ⚋
    -2.09
     to
    -1.99
     If
    -1.81
    ꜆
    -1.75
    béco
    -1.68
    ON
    -1.66
     jika
    -1.64
    borderFill
    -1.63
     hvis
    -1.62
    тари
    -1.62
    POSITIVE LOGITS
    𓆜
    1.99
    鸶
    1.79
     '
    1.78
     publico
    1.78
    今朝
    1.73
     eſſ
    1.73
    ＝＝＝＝
    1.70
    蒟
    1.66
    暑い
    1.63
     sesu
    1.62
    Activations Density 0.007%

    No Known Activations