© 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. 67871
    Prev
    Next
    INDEX
    Explanations

    verbs followed by prepositions

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

    The neuron strongly activates on unusually long, multi-syllable words.

    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
     חיצוניים
    -1.07
    ÕES
    -0.97
     ____________
    -0.97
    pués
    -0.96
     __________
    -0.96
    Preparazione
    -0.96
    常规
    -0.95
     フレーム
    -0.95
    anguard
    -0.94
    вається
    -0.94
    POSITIVE LOGITS
     encarga
    1.09
     Fazit
    1.07
     możemy
    1.02
    pastebin
    0.98
     Erinner
    0.98
    .
    0.97
     apareció
    0.95
    驚く
    0.92
     手作り
    0.91
     estudar
    0.90
    Activations Density 0.066%

    No Known Activations