© 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. 22-GEMMASCOPE-RES-131K
    7. 35367
    Prev
    Next
    INDEX
    Explanations

    support services and programs

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

    The neuron specializes in detecting numeric date tokens—particularly years—in the text.

    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
    気がする
    -1.49
     mengumumkan
    -1.45
     lantaran
    -1.35
    madeus
    -1.34
     anledning
    -1.30
    ligen
    -1.27
     tew
    -1.27
     fhould
    -1.26
    oires
    -1.24
     aanzien
    -1.24
    POSITIVE LOGITS
     services
    2.48
     service
    1.91
    บริการ
    1.66
     programas
    1.66
     provide
    1.61
     programs
    1.59
    ıyors
    1.59
     السياس
    1.55
     work
    1.51
     provider
    1.51
    Activations Density 0.069%

    No Known Activations