© 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. 67011
    Prev
    Next
    INDEX
    Explanations

    programming code or data structures

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

    The neuron fires on occurrences of the “[" token (opening square brackets).

    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
     attirer
    -1.63
     feront
    -1.60
     empêcher
    -1.53
    うれ
    -1.52
     tiveram
    -1.50
     éché
    -1.50
     две
    -1.48
    了个
    -1.48
     têm
    -1.47
     utilidad
    -1.45
    POSITIVE LOGITS
     this
    2.48
     from
    1.73
     when
    1.70
     it
    1.57
     (‘
    1.51
     these
    1.47
     which
    1.46
    眼下
    1.41
     our
    1.41
     minutter
    1.39
    Activations Density 0.006%

    No Known Activations