© 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. 30117
    Prev
    Next
    INDEX
    Explanations

    self-perception and development

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

    The neuron activates on occurrences of the prefix “self” (e.g. in words like self‐care, self‐esteem, self‐objectification, etc.).

    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
     personal
    -0.81
    ogenous
    -0.77
    न्छ
    -0.73
    (")");
    -0.71
    這麼
    -0.71
    如下图
    -0.69
    tamen
    -0.69
    ̗
    -0.69
    ható
    -0.68
    caixa
    -0.65
    POSITIVE LOGITS
     development
    1.27
     discovery
    1.25
     improvement
    1.14
     esteem
    1.10
     control
    1.01
     acceptance
    0.98
     desarrollo
    0.97
     awareness
    0.97
     knowledge
    0.94
     Improvement
    0.92
    Activations Density 0.020%

    No Known Activations