© 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. 22-GEMMASCOPE-RES-131K
    7. 66643
    Prev
    Next
    INDEX
    Explanations

    action to do

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

    This neuron activates on words and short phrases that express capability or permission (e.g. “to work,” “doesn’t support,” “allow,” “cannot,” “should have”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ("")]
    -1.25
    beginTransaction
    -1.09
    Thé
    -1.08
     ६
    -1.06
    danke
    -1.06
    ensivo
    -1.05
     ktorí
    -1.04
    aneously
    -1.03
    setRotation
    -1.03
    :^{
    -1.02
    POSITIVE LOGITS
     itself
    1.72
    itself
    1.20
    见
    1.20
     uman
    1.18
     require
    1.17
     файлы
    1.17
     required
    1.16
     its
    1.16
     yz
    1.14
     Filipinas
    1.08
    Activations Density 0.159%

    No Known Activations