© 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. 3357
    Prev
    Next
    INDEX
    Explanations

    THIS SOFTWARE

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

    The neuron activates on uppercase license‐header keywords (e.g. “THIS,” “SOFTWARE,” “IS”) and Java package/import identifiers (e.g. “plugin,” “.” in fully qualified class names).

    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
    glue
    -0.71
    orsch
    -0.64
     föld
    -0.62
     bergabung
    -0.61
    رائه
    -0.60
     eficiencia
    -0.60
     ancest
    -0.60
     gjelder
    -0.59
     Fácil
    -0.58
     lowa
    -0.58
    POSITIVE LOGITS
     Dei
    0.79
    cide
    0.77
     House
    0.71
    ตู
    0.70
     Jost
    0.69
     Zool
    0.69
    pase
    0.68
    鑫
    0.68
    cida
    0.68
     vit
    0.67
    Activations Density 0.111%

    No Known Activations