© 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. 34-GEMMASCOPE-RES-131K
    7. 58378
    Prev
    Next
    INDEX
    Explanations

    has/is an item

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

    The neuron fires on words that indicate existence or presence checks—e.g. “is,” “are,” “has,” “there,” and “any.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     möj
    -1.03
     possibles
    -0.98
     スリム
    -0.96
    improved
    -0.93
    soit
    -0.90
    橚
    -0.90
    სქ
    -0.88
    corbic
    -0.88
     obrazov
    -0.87
    slightly
    -0.86
    POSITIVE LOGITS
     any
    1.95
     хоть
    1.50
     more
    1.38
     sufficient
    1.27
     other
    1.23
     some
    1.23
    any
    1.23
     valid
    1.23
     errors
    1.23
     хотя
    1.21
    Activations Density 0.116%

    No Known Activations