© 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. 66000
    Prev
    Next
    INDEX
    Explanations

    checking permissions or status

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

    The neuron activates on occurrences of the “chec”/“check” string in words (e.g. “check,” “checkboxes,” etc.).

    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
     archaic
    -1.88
     to
    -1.88
     idyllic
    -1.84
     Such
    -1.84
    -1.79
     That
    -1.76
    哙
    -1.75
     Gründung
    -1.73
    并没有
    -1.71
     начинают
    -1.70
    POSITIVE LOGITS
    ซ์
    2.23
     ftate
    2.03
     the
    2.00
    鄖
    1.96
     Ottobre
    1.92
     kesi
    1.92
    ers
    1.91
     %),
    1.91
     udang
    1.90
     poffe
    1.87
    Activations Density 0.076%
    No Known Activations