© 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. 3685
    Prev
    Next
    INDEX
    Explanations

    self reliance and autonomy

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

    This neuron fires on instructional or how-to language—especially infinitival “to” phrases and modal/imperative verbs indicating steps or actions.

    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
    oscopy
    -0.82
     ს
    -0.78
    SCO
    -0.78
    oscope
    -0.76
     фо
    -0.75
    maro
    -0.75
    pys
    -0.75
    ϯ
    -0.74
    fns
    -0.74
    джа
    -0.74
    POSITIVE LOGITS
     fend
    3.23
     independent
    1.91
     self
    1.89
     independently
    1.87
     самостоя
    1.80
     самостоятельно
    1.70
    independent
    1.66
     tự
    1.59
    自行
    1.56
    自分で
    1.52
    Activations Density 0.029%

    No Known Activations