© 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. 73411
    Prev
    Next
    INDEX
    Explanations

    alternatives or contrasts

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

    The neuron activates on the letter sequence “or,” whether as the standalone word or embedded within another word.

    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
    ↵
    -1.68
    piecze
    -1.63
    Արտաքին
    -1.62
     éves
    -1.60
     Also
    -1.52
     også
    -1.46
    鲽
    -1.44
    Ộ
    -1.43
    き
    -1.42
    regated
    -1.41
    POSITIVE LOGITS
     decorativa
    1.78
     universitaria
    1.73
     creativa
    1.61
    \
    1.59
    between
    1.59
    何より
    1.45
     blanda
    1.45
     البته
    1.44
    ,
    1.44
    感じです
    1.42
    Activations Density 0.051%

    No Known Activations