© 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. 34-GEMMASCOPE-RES-131K
    7. 117194
    Prev
    Next
    INDEX
    Explanations

    Elizabeth followed by a surname

    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_34/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
    PROBE
    -0.88
    jaci
    -0.83
    بري
    -0.82
    keyValue
    -0.81
     世
    -0.78
     milioane
    -0.75
    غل
    -0.75
     Jew
    -0.75
    regener
    -0.73
    
    -0.73
    POSITIVE LOGITS
    晚安
    0.89
    镜子
    0.89
    入り口
    0.77
     всей
    0.74
    ಿನ
    0.72
    マフラー
    0.71
     Salón
    0.71
    苫
    0.70
     magnify
    0.70
     üzer
    0.70
    Activations Density 0.011%

    No Known Activations