© 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. 48016
    Prev
    Next
    INDEX
    Explanations

    isoform

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

    The neuron detects proper nouns, particularly names of people, chemical compounds, and specialized terminology (like "isoform").

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ),
    -3.72
    =
    -2.92
    1
    -2.88
     We
    -2.84
    {
    -2.78
    .,
    -2.56
    _
    -2.56
    >
    -2.55
    ?
    -2.53
    に行って
    -2.38
    POSITIVE LOGITS
    i
    3.22
    ጵ
    3.09
    ي
    2.97
    ၜ
    2.83
    ᠂
    2.61
    ”،
    2.56
    ୩
    2.53
    
    2.52
    慙
    2.50
    摃
    2.48
    Activations Density 0.052%

    No Known Activations