© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 75093
    Prev
    Next
    INDEX
    Explanations

    i, i've

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

    This neuron detects occurrences of the first‐person pronoun “I” (and forms like “I’m”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     of
    -1.89
    </td>
    -1.83
     даже
    -1.65
     would
    -1.63
     "
    -1.63
    d
    -1.59
    p
    -1.57
    k
    -1.52
    g
    -1.51
    </h2>
    -1.42
    POSITIVE LOGITS
     giy
    1.56
     tekno
    1.54
    tiness
    1.52
    
    1.51
    aimana
    1.48
     personlig
    1.47
     enlever
    1.47
     撮り
    1.45
    wasn
    1.45
    partly
    1.45
    Activations Density 0.143%

    No Known Activations