© 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. 70162
    Prev
    Next
    INDEX
    Explanations

    strict or lenient settings

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

    This neuron detects code identifiers in CamelCase (especially struct field names) in source files.

    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
    ണം
    -0.78
     Herbst
    -0.76
    ➷
    -0.76
    的時間
    -0.76
     resettlement
    -0.76
     hudeb
    -0.75
     ایجاد
    -0.75
    enderita
    -0.74
    rimid
    -0.74
    ترن
    -0.71
    POSITIVE LOGITS
     tolerate
    1.70
     tolerance
    1.52
     tolerant
    1.48
     allow
    1.33
     ALLOW
    1.32
     strict
    1.32
     Toler
    1.30
     toler
    1.27
     tolerated
    1.25
     lenient
    1.25
    Activations Density 0.099%

    No Known Activations