© 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. 10-GEMMASCOPE-RES-131K
    7. 3605
    Prev
    Next
    INDEX
    Explanations

    theorem

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

    The neuron specializes in spotting occurrences of the word “theorem.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     \&
    -2.94
     was
    -2.92
    ?"
    -2.78
    柒
    -2.70
    潆
    -2.53
    arschu
    -2.41
    。
    -2.41
     bzw
    -2.41
     или
    -2.39
    는
    -2.39
    POSITIVE LOGITS
    .
    4.63
    ↵↵
    3.41
    The
    3.02
    >
    2.97
    <i>
    2.53
    </i>
    2.41
    B
    2.41
    箆
    2.33
    鹬
    2.33
    ly
    2.31
    Activations Density 0.010%

    No Known Activations