© 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. 34-GEMMASCOPE-RES-131K
    7. 58261
    Prev
    Next
    INDEX
    Explanations

    educational institutions and their associations

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

    This neuron responds to capitalized tokens—proper names, headings, institutions, months, acronyms, and other words beginning with an uppercase letter.

    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
    ')")
    -0.95
    ଶ
    -0.84
    🐕
    -0.84
     plaît
    -0.82
     拌
    -0.81
     Chapitre
    -0.80
     CHAPITRE
    -0.79
     optik
    -0.79
     khawatir
    -0.79
     vrouw
    -0.79
    POSITIVE LOGITS
     their
    1.02
     V
    0.93
    ·
    0.90
     focuses
    0.88
     Their
    0.88
     also
    0.84
     ਫ
    0.84
    ie
    0.84
     no
    0.84
    den
    0.84
    Activations Density 0.003%

    No Known Activations