© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99367
    Prev
    Next
    INDEX
    Explanations

    compound words starting with Full

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

    This neuron primarily activates on occurrences of the word “Full.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    seems
    -0.95
    脍
    -0.95
    ajo
    -0.83
    idencia
    -0.82
     inmueble
    -0.82
     неболь
    -0.78
    шое
    -0.78
    Seems
    -0.77
    relatively
    -0.77
    áli
    -0.77
    POSITIVE LOGITS
    fledged
    1.73
     full
    1.53
    Full
    1.52
    full
    1.48
     fled
    1.48
     extent
    1.43
     blown
    1.39
     length
    1.36
     throttle
    1.34
     spectrum
    1.33
    Activations Density 0.037%

    No Known Activations