© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129013
    Prev
    Next
    INDEX
    Explanations

    If I

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

    The neuron is triggered by first-person singular pronouns—especially “I”—in statements (e.g. “I did,” “If I understood,” 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_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
     nî
    -1.48
    ,
    -1.38
     prado
    -1.32
     Méd
    -1.30
     daer
    -1.27
     resté
    -1.25
     fono
    -1.24
    کننده
    -1.24
     eene
    -1.23
     raiſ
    -1.23
    POSITIVE LOGITS
    If
    1.59
     If
    1.56
     if
    1.51
    2
    1.42
    al
    1.35
     cosas
    1.35
    ꔹ
    1.33
    7
    1.33
    的机会
    1.32
    等我
    1.32
    Activations Density 0.047%

    No Known Activations