© 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. 53833
    Prev
    Next
    INDEX
    Explanations

    things ending

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

    The neuron is strongly activated by function words—especially personal pronouns (“I,” “we,” “they”) and auxiliary/modal words (“may,” “could,” “’ll,” “just,” “so,” “but”).

    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
    仑
    -0.80
    ⌥
    -0.80
    _=
    -0.79
    NESSEE
    -0.79
    inston
    -0.77
     möchten
    -0.76
     varför
    -0.74
     først
    -0.74
    reszcie
    -0.74
     fliegen
    -0.73
    POSITIVE LOGITS
     ended
    5.50
     ends
    4.78
     end
    4.75
     ending
    3.98
    Ended
    3.84
     Ended
    3.84
    ended
    3.72
     wound
    3.39
     Ends
    3.31
     winds
    3.11
    Activations Density 0.158%

    No Known Activations