© 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. 76006
    Prev
    Next
    INDEX
    Explanations

    lessons and teaching

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

    This neuron detects sequences of capitalized words, as in titles or headings.

    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
    ulink
    -0.93
    tisseur
    -0.87
     Durchführung
    -0.82
     research
    -0.78
    Infinity
    -0.77
     preseason
    -0.75
    Research
    -0.74
    電腦
    -0.74
    JsonHelper
    -0.74
    Iglesia
    -0.73
    POSITIVE LOGITS
     lessons
    1.41
     lesson
    1.26
     boys
    1.26
    lessons
    1.21
     pupils
    1.20
     Lessons
    1.13
    Lessons
    1.12
     pelajaran
    1.11
     girls
    1.10
     teachers
    1.09
    Activations Density 0.026%

    No Known Activations