© 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. 99598
    Prev
    Next
    INDEX
    Explanations

    worksheets

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

    The neuron specifically responds to occurrences of the word “worksheet” (including its plural “worksheets”).

    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
    ⎔
    -2.64
     จะ
    -2.53
     minimale
    -2.47
    が起こ
    -2.45
     dieser
    -2.45
     มี
    -2.41
    ’
    -2.34
    睃
    -2.33
     intelligente
    -2.33
    并未
    -2.28
    POSITIVE LOGITS
    ll
    3.64
    to
    3.00
    <strong>
    2.97
    n
    2.84
    <em>
    2.83
                    
    2.83
    The
    2.80
    C
    2.70
     untuk
    2.69
    </strong>
    2.63
    Activations Density 0.004%

    No Known Activations