© 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. 59517
    Prev
    Next
    INDEX
    Explanations

    chemical elements and nuclei

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

    chemical elements and scientific notation in academic/scientific papers.

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

    This neuron activates on structural and formatting elements of scientific documents—especially section headings, LaTeX‐style separators, and numbered labels.

    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
    Geografie
    -0.77
    精品
    -0.76
    boat
    -0.74
    tens
    -0.73
    žio
    -0.72
    ſion
    -0.71
    boats
    -0.70
    春日
    -0.70
    adjective
    -0.70
    ristiano
    -0.70
    POSITIVE LOGITS
     iron
    0.94
     nuclei
    0.92
     heavier
    0.91
     Iron
    0.90
     lighter
    0.89
     lightest
    0.85
    จำ
    0.84
    Iron
    0.82
     heavy
    0.82
    Carbon
    0.79
    Activations Density 0.028%

    No Known Activations