© 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. 105435
    Prev
    Next
    INDEX
    Explanations

    words starting with ful

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

    The neuron consistently fires on tokens containing the substring “Ful.”

    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
     enviable
    -2.83
     continúas
    -2.67
     szczeg
    -2.63
     französische
    -2.56
     dando
    -2.50
    蟷
    -2.48
    睒
    -2.48
     wzgl
    -2.48
    )...
    -2.45
     unrival
    -2.45
    POSITIVE LOGITS
    We
    3.77
    ’
    3.63
    Now
    3.47
    This
    3.41
    If
    3.23
     είναι
    3.23
    Our
    3.20
    1
    3.08
    After
    2.94
    While
    2.83
    Activations Density 0.005%

    No Known Activations