© 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. 30202
    Prev
    Next
    INDEX
    Explanations

    `Selector('#`

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

    The neuron strongly activates on literal configuration keys and constants in code (e.g. things like `'test'`, `test_entry_url`, and other config/constant identifiers).

    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
     Caribe
    -0.79
     piper
    -0.79
     бума
    -0.78
     siempre
    -0.77
     sinistra
    -0.77
     blanket
    -0.76
    ִּ
    -0.75
    套餐
    -0.71
    וּ
    -0.71
     Abon
    -0.71
    POSITIVE LOGITS
     вижу
    0.79
    væ
    0.75
    わけではない
    0.74
    hashes
    0.74
    ürgen
    0.73
     Functional
    0.72
     Fixtures
    0.72
     alice
    0.71
     fibro
    0.70
    IPPED
    0.70
    Activations Density 0.006%

    No Known Activations