© 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. 42591
    Prev
    Next
    INDEX
    Explanations

    programming, ui, and specific nouns

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

    The neuron responds to unusually long individual tokens (i.e. long words).

    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
    ↵↵
    -2.95
    _
    -2.61
     –
    -2.56
    p
    -2.48
    x
    -2.34
    </i>
    -2.33
     make
    -2.28
    :
    -2.25
    あります
    -2.19
    (
    -2.19
    POSITIVE LOGITS
     serían
    2.83
    淠
    2.73
     permanece
    2.59
    ...";
    2.58
    ...',
    2.52
    
    2.50
    yarakat
    2.48
     سامسون
    2.45
     actúa
    2.45
     ſaid
    2.41
    Activations Density 0.008%

    No Known Activations