© 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. 32208
    Prev
    Next
    INDEX
    Explanations

    questions about math and calculus

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

    The neuron fires on verbs that describe a person’s actions or capabilities (e.g. “started,” “studied,” “can do,” “manage”), especially in self‐descriptive contexts.

    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
     people
    -0.96
     thất
    -0.90
    װ
    -0.86
    －－
    -0.85
    zard
    -0.82
    warted
    -0.82
    Ϲ
    -0.82
    Terra
    -0.81
    査
    -0.81
    dier
    -0.78
    POSITIVE LOGITS
     topic
    1.05
     topics
    0.99
     concepts
    0.98
     scoring
    0.97
     chapters
    0.95
     theorems
    0.91
    concept
    0.89
     maus
    0.87
     theoretical
    0.86
    Attempt
    0.85
    Activations Density 0.023%

    No Known Activations