© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 9627
    Prev
    Next
    INDEX
    Explanations

    existence or occurrence

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

    This neuron activates on the main topic or object noun of a question or statement, highlighting the key technical term or issue being discussed.

    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
     to
    -1.46
     aussit
    -1.29
     tekem
    -1.17
    ございません
    -1.16
    的一切
    -1.13
    –
    -1.09
     eivät
    -1.09
    standen
    -1.08
     signifikan
    -1.08
     melahirkan
    -1.06
    POSITIVE LOGITS
     are
    2.11
     is
    2.03
     occurs
    1.78
     was
    1.77
     exists
    1.75
     exist
    1.61
     occur
    1.55
     will
    1.52
     come
    1.40
     otros
    1.40
    Activations Density 0.166%

    No Known Activations