© 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. 22-GEMMASCOPE-RES-131K
    7. 15703
    Prev
    Next
    INDEX
    Explanations

    questions and statements

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

    The neuron is keyed to first-person “I” statements, strongly activating on the pronoun “I” when people relate personal experiences or opinions.

    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
    taya
    -1.13
     Wortes
    -1.13
     merkwür
    -1.07
    なかな
    -1.05
    حه
    -1.05
     optimieren
    -1.04
     tomto
    -1.02
    Ǿ
    -1.02
     betreffenden
    -1.02
    chrift
    -1.00
    POSITIVE LOGITS
     they
    1.64
     my
    1.38
     I
    1.17
     so
    1.16
     just
    1.16
    ≜
    1.05
     it
    1.05
     seem
    1.02
    <h2>
    0.99
     since
    0.95
    Activations Density 0.106%

    No Known Activations