© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21165
    Prev
    Next
    INDEX
    Explanations

    CSE UNC CSA

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

    The neuron activates on uppercase multi‐letter acronyms or initialisms (e.g. “UNC,” “CSE,” “CSA”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    
    -3.14
    湏
    -2.98
     praktische
    -2.55
    塍
    -2.52
    洨
    -2.45
     They
    -2.41
    閙
    -2.30
     jezt
    -2.27
    ↵↵
    -2.23
     podem
    -2.23
    POSITIVE LOGITS
    as
    3.05
    One
    2.72
    to
    2.72
    A
    2.70
    Some
    2.69
    because
    2.69
    In
    2.67
    E
    2.64
    Several
    2.61
    Many
    2.52
    Activations Density 0.003%

    No Known Activations