© 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. 91024
    Prev
    Next
    INDEX
    Explanations

    i begin or start

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

    This neuron detects first-person references, specifically the pronoun "I" (and its contractions like "I’ve").

    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
     Also
    -1.34
     también
    -1.30
     from
    -1.28
     and
    -1.27
     także
    -1.23
    Also
    -1.23
     also
    -1.23
     etiam
    -1.17
     in
    -1.17
     on
    -1.13
    POSITIVE LOGITS
     first
    1.88
     originally
    1.80
     initially
    1.59
     první
    1.52
     was
    1.48
     ابتدا
    1.46
     recently
    1.45
     wasn
    1.44
     started
    1.37
     primeira
    1.36
    Activations Density 0.101%

    No Known Activations