© 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. 128848
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on technical or scientific measurement language—especially terms and values related to instrumentation and quantitative analysis.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    forms of to be

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     when
    -2.06
     infatti
    -1.74
     then
    -1.74
     but
    -1.72
     therefore
    -1.61
     azonban
    -1.57
     inoltre
    -1.52
     However
    -1.48
     поэтому
    -1.48
    になりますが
    -1.48
    POSITIVE LOGITS
     blant
    1.22
    further
    1.20
     craindre
    1.15
     „
    1.14
     coreano
    1.13
     outros
    1.13
    abili
    1.13
     другую
    1.12
     diverses
    1.11
    ANEOUS
    1.11
    Activations Density 0.040%

    No Known Activations