© 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. 34-GEMMASCOPE-RES-131K
    7. 92139
    Prev
    Next
    INDEX
    Explanations

    duchenne, chen, chan, cho, cher

    np_acts-logits-general · gemini-2.5-flash-lite

    surnames ending with "chen" or similar sounds like "chers" and "choa".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ต่างๆ
    -0.81
     conquista
    -0.81
    ᶦ
    -0.81
    cils
    -0.77
    وروب
    -0.75
    Iglesia
    -0.75
    كتشاف
    -0.74
     religi
    -0.73
     побу
    -0.73
     картин
    -0.72
    POSITIVE LOGITS
    ersonal
    0.81
     TEN
    0.80
    τή
    0.79
     эмоциона
    0.77
     SHOULD
    0.75
     coop
    0.73
     pasirink
    0.73
     HY
    0.73
    signals
    0.73
     Construct
    0.73
    Activations Density 0.067%

    No Known Activations