© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 97940
    Prev
    Next
    INDEX
    Explanations

    true RequirementsMode

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

    This neuron responds to programming‐related identifiers—especially CamelCase names and code tokens (e.g. class/attribute/method 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
    dwelling
    -0.85
     `,
    -0.80
     Теперь
    -0.80
     البيت
    -0.78
    𝜌
    -0.77
    ᱽ
    -0.77
    反应过来
    -0.76
     lords
    -0.75
     soutě
    -0.75
    JACK
    -0.73
    POSITIVE LOGITS
     column
    0.74
    憬
    0.73
    sue
    0.72
    :]:
    0.71
     columns
    0.71
    fill
    0.70
    Column
    0.70
     Reiki
    0.69
     fill
    0.68
    вания
    0.68
    Activations Density 0.001%

    No Known Activations