© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79042
    Prev
    Next
    INDEX
    Explanations

    only to do

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

    The neuron strongly responds to occurrences of the adverb “only.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    れません
    -1.06
    就要
    -1.05
     autre
    -0.97
     függ
    -0.89
     évidence
    -0.89
     Einzelnen
    -0.87
    ckeye
    -0.85
     zarówno
    -0.85
     jungen
    -0.85
    नु
    -0.84
    POSITIVE LOGITS
     to
    2.89
     then
    1.39
     podľa
    1.08
     kemudian
    1.03
    ecuzione
    1.01
     it
    1.01
     spôso
    0.97
     žiad
    0.97
     find
    0.95
     later
    0.95
    Activations Density 0.017%

    No Known Activations