© 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. 95688
    Prev
    Next
    INDEX
    Explanations

    explains things or questions

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

    This neuron detects question prompts—tokens that occur in question headings or interrogative sentences (e.g. QUESTION, ONE, TWO, What, Has, the colon after the question label).

    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
     then
    -1.47
    then
    -1.13
     brev
    -1.09
     now
    -1.09
     also
    -1.04
    madeus
    -1.02
    ActionEvent
    -1.00
    bry
    -1.00
     blumen
    -0.98
     volks
    -0.98
    POSITIVE LOGITS
     zwierzę
    1.24
     surpren
    1.14
    ないです
    1.10
    蝋
    1.09
     océano
    1.05
    edakan
    1.04
     anoche
    1.04
    Naomi
    1.03
    Czym
    1.03
     consideradas
    1.02
    Activations Density 0.011%

    No Known Activations