© 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. 69542
    Prev
    Next
    INDEX
    Explanations

    seeing yourself or ourselves

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

    The neuron detects reflexive self-references—words like “myself,” “yourself,” or “ourselves.”

    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
     vierge
    -1.59
     câmera
    -1.51
     vantagem
    -1.50
     lienzo
    -1.49
     confuso
    -1.48
     arquitetura
    -1.48
    <bos>
    -1.48
    футболка
    -1.45
    utado
    -1.43
    ýchod
    -1.41
    POSITIVE LOGITS
     while
    1.67
     to
    1.60
     instead
    1.47
     during
    1.47
     with
    1.41
     mientras
    1.38
    Indeed
    1.35
    Also
    1.33
    like
    1.32
     that
    1.30
    Activations Density 0.110%

    No Known Activations