© 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. 34-GEMMASCOPE-RES-131K
    7. 115705
    Prev
    Next
    INDEX
    Explanations

    it followed by verb or 's

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

    This neuron responds to common short function words (e.g. pronouns and auxiliary verbs) rather than content 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_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
     نیز
    -1.16
    Controllo
    -1.12
    Soon
    -1.10
     maakte
    -1.09
     számára
    -1.08
     également
    -1.03
     Meski
    -1.03
    鑷
    -1.00
     tevé
    -1.00
     kérd
    -1.00
    POSITIVE LOGITS
     [
    2.20
     kind
    1.94
     somebody
    1.73
     really
    1.65
     actually
    1.51
     anybody
    1.45
     everybody
    1.45
     sort
    1.43
     kinda
    1.43
     maybe
    1.39
    Activations Density 0.012%

    No Known Activations