© 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. 39874
    Prev
    Next
    INDEX
    Explanations

    citations and abbreviations

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

    The neuron responds to numerical tokens—especially decimal numbers and stats—typically found in citations, volume/page references, or percentage figures.

    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
     kupa
    -1.52
     medy
    -1.50
    芒果
    -1.45
     atak
    -1.44
    ,
    -1.41
     باتری
    -1.38
    ïc
    -1.38
     etap
    -1.35
    ñor
    -1.34
    räder
    -1.33
    POSITIVE LOGITS
    ↵↵
    2.33
     its
    1.93
     difficoltà
    1.74
     simply
    1.74
     wrongly
    1.63
     zawsze
    1.59
     porque
    1.56
     notwendigen
    1.56
     always
    1.52
    本身
    1.49
    Activations Density 0.025%

    No Known Activations