© 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. 10-GEMMASCOPE-RES-131K
    7. 111454
    Prev
    Next
    INDEX
    Explanations

    technical nouns

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

    technical or specialized terminology, particularly related to technology, medicine, and software.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires strongly on standalone content nouns—especially concrete or technical terms.

    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
     only
    -2.22
     and
    -1.95
     should
    -1.73
    With
    -1.63
    [
    -1.56
    Both
    -1.55
     wyłącznie
    -1.55
    Only
    -1.48
     Neither
    -1.48
     no
    -1.46
    POSITIVE LOGITS
     maniere
    1.48
    vermectin
    1.41
    錾
    1.41
    vänt
    1.40
     of
    1.39
     secoli
    1.38
    MANY
    1.38
    nimmt
    1.35
    찡
    1.33
     zodia
    1.32
    Activations Density 0.249%

    No Known Activations