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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1739
    Prev
    Next
    INDEX
    Explanations

    code structures and specific phrases

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

    The neuron fires on PHP code identifiers—especially CamelCase class, interface, and namespace 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
    Тогда
    -0.78
     boycot
    -0.78
    ttar
    -0.75
     случаев
    -0.75
     ids
    -0.72
     manner
    -0.72
    けれ
    -0.71
    держание
    -0.71
    明明
    -0.69
    icolon
    -0.69
    POSITIVE LOGITS
    дие
    0.88
     Slim
    0.82
     Verse
    0.82
    Slim
    0.80
    Factories
    0.79
     Mezz
    0.78
    Container
    0.77
    NJ
    0.76
    Philippine
    0.75
     <?=
    0.74
    Activations Density 0.016%

    No Known Activations