© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84323
    Prev
    Next
    INDEX
    Explanations

    college campuses and applied science

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

    The neuron strongly activates on standalone numbers, hyphens, and other tokens used in structured headings or list‐style metadata (e.g. dates, numeric entries, and section separators).

    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
     Processor
    -0.71
    imente
    -0.70
     universities
    -0.70
    lieder
    -0.69
    حيات
    -0.69
     eyebrows
    -0.68
     Cowley
    -0.68
     Cupcakes
    -0.67
     biscuit
    -0.67
     Prayer
    -0.67
    POSITIVE LOGITS
     college
    1.08
     Applied
    0.90
     applied
    0.83
    Applied
    0.82
    RUNTIME
    0.74
    類
    0.74
    COLLEGE
    0.72
    ']['
    0.72
    applied
    0.71
     pneumo
    0.68
    Activations Density 0.025%

    No Known Activations