© 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. 34-GEMMASCOPE-RES-131K
    4. 84019
    Prev
    Next
    INDEX
    Explanations

    turning to look suddenly

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

    The neuron is keyed to self- or reader-referential language—strongly activating on first- and second-person pronouns (“I,” “you,” “me”) and the immediate verbs/actions tied to them.

    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
    vdots
    -0.83
    −/−
    -0.81
    幄
    -0.81
     kembali
    -0.80
     Again
    -0.78
    сшта
    -0.77
     Direito
    -0.76
     לאחר
    -0.75
    ggars
    -0.75
     rękaw
    -0.75
    POSITIVE LOGITS
     startled
    1.73
    振り
    1.18
     looked
    1.12
     look
    1.03
     surprised
    1.02
     instantly
    1.01
     lifting
    0.99
     alarmed
    0.95
     instantaneously
    0.90
     curious
    0.89
    Activations Density 0.013%

    No Known Activations