© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44164
    Prev
    Next
    INDEX
    Explanations

    medical/scientific terms

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

    scientific and technical terms related to specialized fields like electron resonance, microbiology, and wireless technologies.

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

    This neuron detects mentions of electron spin‐resonance spectroscopy (e.g. “spin resonance,” “EPR,” “electron paramagnetic resonance”).

    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
    warnai
    -1.55
    THO
    -1.46
    ников
    -1.45
     già
    -1.35
    äfts
    -1.32
     historische
    -1.32
    BITDA
    -1.32
     pequeñas
    -1.31
    ERÍA
    -1.31
     También
    -1.30
    POSITIVE LOGITS
     then
    2.58
     kemudian
    1.61
     because
    1.59
    es
    1.47
     to
    1.45
     that
    1.44
    因为它
    1.42
     here
    1.40
     now
    1.39
     want
    1.38
    Activations Density 0.137%

    No Known Activations