© 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. 98610
    Prev
    Next
    INDEX
    Explanations

    I, me, my

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

    The neuron fires strongly on the very first few words of a new sentence or paragraph (especially when it begins with a capitalized pronoun like “I,” “They,” etc.).

    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
     désolés
    -0.96
     menerapkan
    -0.93
    сели
    -0.93
     consci
    -0.90
     vana
    -0.89
     aktivi
    -0.88
     gustado
    -0.87
     kny
    -0.87
    Dibrom
    -0.86
     bodyParser
    -0.85
    POSITIVE LOGITS
     I
    1.92
     me
    1.34
     my
    1.27
     tôi
    1.17
     then
    1.13
     he
    0.93
     allora
    0.90
    ผม
    0.90
     so
    0.88
    ėjimas
    0.87
    Activations Density 0.070%

    No Known Activations