© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 124759
    Prev
    Next
    INDEX
    Explanations

    "OK" or "Okay"

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

    The neuron fires for occurrences of the token “OK,” i.e. the “OK” button/label in dialogs or forms.

    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
     такие
    -1.63
    such
    -1.54
     takie
    -1.53
     such
    -1.53
    ㉕
    -1.52
     listop
    -1.49
     trener
    -1.48
     generazione
    -1.48
     takimi
    -1.46
     após
    -1.45
    POSITIVE LOGITS
    Although
    1.59
     Although
    1.46
     variante
    1.40
    il
    1.39
    There
    1.37
    ramientas
    1.34
     comparatively
    1.32
    居酒屋
    1.32
     viable
    1.29
    د
    1.29
    Activations Density 0.035%

    No Known Activations