© 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. 10-GEMMASCOPE-RES-131K
    7. 8629
    Prev
    Next
    INDEX
    Explanations

    this is

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

    The neuron fires on occurrences of the present‐tense copula “is,” especially in “This is”-style phrases.

    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
    &$
    -1.41
    匮
    -1.37
     mener
    -1.35
     accompagné
    -1.34
     biens
    -1.34
    tise
    -1.32
    ⩤
    -1.30
     écoute
    -1.29
    rium
    -1.28
     yeri
    -1.28
    POSITIVE LOGITS
     required
    1.46
     intended
    1.42
     too
    1.41
     ‘
    1.41
     designed
    1.38
     now
    1.37
     There
    1.37
     initially
    1.35
     had
    1.30
     although
    1.30
    Activations Density 0.043%

    No Known Activations