© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 75146
    Prev
    Next
    INDEX
    Explanations

    is a/an/the

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

    The neuron fires on the linking verb “is” when it’s used in an introductory “X is Y”–style definitional or descriptive phrase (especially “This is …”).

    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
     this
    -2.03
    總是
    -1.55
    ができます
    -1.48
     geef
    -1.45
     acestei
    -1.44
     gewicht
    -1.39
     olje
    -1.38
    ☆☆☆☆☆
    -1.38
     этого
    -1.36
     frontale
    -1.36
    POSITIVE LOGITS
     a
    2.27
     an
    1.77
     how
    1.49
     -
    1.44
     –
    1.29
     czerwca
    1.28
    いわゆる
    1.28
     lutego
    1.28
     как
    1.24
     /
    1.20
    Activations Density 0.112%

    No Known Activations