© 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. 10-GEMMASCOPE-RES-131K
    7. 84324
    Prev
    Next
    INDEX
    Explanations

    is a kind of

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

    This neuron detects occurrences of the linking verb “is” (and its equivalents in other languages) used as a copula.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     and
    -1.90
    4
    -1.88
    9
    -1.67
    \
    -1.66
    2
    -1.59
    6
    -1.51
    nehå
    -1.49
    8
    -1.47
    7
    -1.44
    5
    -1.40
    POSITIVE LOGITS
     a
    1.89
     spiega
    1.59
     some
    1.49
    DREN
    1.48
     having
    1.46
     newfound
    1.45
     vitrine
    1.44
     nors
    1.43
    prime
    1.42
     brinquedo
    1.42
    Activations Density 0.002%

    No Known Activations