© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66799
    Prev
    Next
    INDEX
    Explanations

    president, general, secretary, queen

    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
     ceux
    -1.52
     illustrate
    -1.49
    ḿ
    -1.48
    
    -1.47
    リル
    -1.42
     οι
    -1.41
    レッチ
    -1.41
    .}
    -1.41
    他的
    -1.41
    问道
    -1.41
    POSITIVE LOGITS
     if
    1.79
    5
    1.57
    Ｅ
    1.49
    ＝
    1.48
    9
    1.46
     היתה
    1.46
    The
    1.46
    0
    1.42
    peugeot
    1.42
    Répondre
    1.42
    Activations Density 0.773%

    No Known Activations