© 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. 22-GEMMASCOPE-RES-131K
    7. 72912
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts

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

    The neuron primarily detects long, specialized technical or scientific terminology.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     «
    -1.80
    en
    -1.63
    l
    -1.57
    P
    -1.56
     •
    -1.55
    di
    -1.54
    g
    -1.45
    oo
    -1.45
    an
    -1.44
    to
    -1.43
    POSITIVE LOGITS
     plafon
    1.95
    Jalan
    1.59
     Règlement
    1.57
    Buku
    1.56
    ஏ
    1.52
     工房
    1.49
     收納
    1.48
     incrí
    1.48
     Voulez
    1.48
     ecran
    1.47
    Activations Density 0.058%

    No Known Activations