© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 75136
    Prev
    Next
    INDEX
    Explanations

    skull study, skull base, crystal skull

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

    The neuron detects references to skulls, craniums, and skull-related anatomical terms.

    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_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
    芣
    -3.05
    就算是
    -2.80
    ar
    -2.70
    The
    -2.66
    -"
    -2.56
     –
    -2.56
    ть
    -2.56
    
    -2.50
    es
    -2.41
    """
    -2.41
    POSITIVE LOGITS
    linawan
    2.47
    晄
    2.41
    <bos>
    2.39
     respective
    2.34
     putative
    2.28
    弢
    2.25
     meget
    2.23
     example
    2.19
    驀
    2.17
    壅
    2.14
    Activations Density 0.006%

    No Known Activations