© 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. 10-GEMMASCOPE-RES-131K
    4. 130612
    Prev
    Next
    INDEX
    Explanations

    place names and organizations

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

    The neuron strongly activates on numeric tokens—years, section or figure numbers, and other digit‐based references.

    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
    '
    -2.11
     "
    -1.63
     for
    -1.59
    \
    -1.51
     where
    -1.47
     if
    -1.44
     woman
    -1.41
     discernible
    -1.40
     Männern
    -1.36
    褔
    -1.34
    POSITIVE LOGITS
    quelize
    1.75
     of
    1.68
     één
    1.67
    ;
    
    1.61
    ၞ
    1.59
    brtc
    1.56
    llten
    1.56
    ixante
    1.55
    Autoritní
    1.55
    */
    
    1.55
    Activations Density 0.070%

    No Known Activations