© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100384
    Prev
    Next
    INDEX
    Explanations

    Wiley version

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

    The neuron strongly activates on the characteristic morphemes of technical scientific terms—especially Latin/Greek‐derived roots and suffixes in chemical, botanical, geological, or clinical names.

    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
     verbess
    -1.96
    .
    -1.94
    la
    -1.85
    le
    -1.75
    一旁
    -1.59
     de
    -1.59
    錵
    -1.59
    ne
    -1.59
    味的
    -1.57
    他的
    -1.52
    POSITIVE LOGITS
    ïlande
    1.65
    迓
    1.65
    砗
    1.65
    '):
    
    1.62
    ╿
    1.59
    捫
    1.57
    плення
    1.56
     hauptsächlich
    1.55
     fraternity
    1.55
    )$,
    1.55
    Activations Density 0.001%

    No Known Activations