© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106293
    Prev
    Next
    INDEX
    Explanations

    chime in and announce

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

    The neuron activates on words that name or refer to people or personal agents—pronouns and nouns identifying individuals (e.g. “I,” “man,” “lady,” “everyone”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    discus
    -0.88
     esplor
    -0.88
    ugas
    -0.77
     wizy
    -0.77
    文句
    -0.77
     utilizz
    -0.76
    zeera
    -0.76
     worden
    -0.75
     ricor
    -0.75
     weiterhin
    -0.75
    POSITIVE LOGITS
     chime
    3.67
     chi
    3.34
     chimes
    3.11
    Chi
    2.23
     Chi
    2.11
     piped
    2.11
     pipes
    2.08
     pipe
    2.05
     intervene
    2.02
     chim
    1.97
    Activations Density 0.037%

    No Known Activations