© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 40535
    Prev
    Next
    INDEX
    Explanations

    DNA fragmentation

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

    scientific terminology and organisms, particularly diatoms and other microorganisms.

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

    This neuron fires on scientific and technical terms—especially chemical (e.g. silicon/silicate) and biological taxa (e.g. diatom/diatoms, Giardia, dinoflagellate) vocabulary.

    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
     —
    -1.99
     These
    -1.88
    al
    -1.84
    1
    -1.80
     This
    -1.73
     aktuellen
    -1.72
    ри
    -1.69
     Europäischen
    -1.68
     We
    -1.67
     Including
    -1.66
    POSITIVE LOGITS
     continúas
    2.33
    乸
    1.92
     rápidas
    1.87
     probado
    1.80
    顶部
    1.77
    Ḣ
    1.74
     mencionado
    1.73
     使っ
    1.72
     preparados
    1.71
    словно
    1.68
    Activations Density 0.009%

    No Known Activations