© 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. 9262
    Prev
    Next
    INDEX
    Explanations

    to followed by verbs

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

    The neuron fires on verbs that express making a choice or decision (e.g., “choose,” “chose,” “choosing,” “make”).

    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
     causing
    -1.87
    鉝
    -1.86
     continúas
    -1.78
    </strong>
    -1.77
     blanca
    -1.75
     pertaining
    -1.75
     trying
    -1.73
     changes
    -1.71
     any
    -1.68
     implementing
    -1.68
    POSITIVE LOGITS
    $
    2.20
    2
    2.08
    1
    2.03
    或者
    1.84
     tainted
    1.77
    4
    1.76
    however
    1.68
     แต่
    1.63
     BECAUSE
    1.61
    9
    1.61
    Activations Density 0.007%

    No Known Activations