© 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. 10-GEMMASCOPE-RES-131K
    7. 66602
    Prev
    Next
    INDEX
    Explanations

    echinococcosis and coccidiosis

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

    scientific and technical terminology, particularly biological terms like proteins, enzymes, and file formats.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on infrequent, specialized tokens—i.e. rare or domain‐specific words—regardless of subject.

    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
    After
    -1.88
    What
    -1.88
     two
    -1.86
    Two
    -1.84
    𞤤
    -1.72
     fifteen
    -1.65
    两个
    -1.63
     setelah
    -1.63
     after
    -1.60
     mostly
    -1.59
    POSITIVE LOGITS
    !!!!!!!
    1.46
    through
    1.41
    になれば
    1.36
    茈
    1.36
    立马
    1.34
     of
    1.31
    ⸰
    1.31
    却被
    1.30
    commonly
    1.30
     rar
    1.27
    Activations Density 0.147%

    No Known Activations