© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12844
    Prev
    Next
    INDEX
    Explanations

    graphics code and coordinates

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

    The neuron fires on numeric literals (e.g. coordinate, dimension, or other number tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     time
    -1.02
     to
    -1.00
    baro
    -0.96
     mendengar
    -0.93
    isait
    -0.91
    ших
    -0.89
    stram
    -0.88
    衞
    -0.88
     литров
    -0.88
     procedure
    -0.87
    POSITIVE LOGITS
    Gön
    1.15
    旃
    1.13
    Hadi
    1.02
     then
    1.00
    ᾷ
    0.99
    Краси
    0.97
     꽃
    0.94
     Jambi
    0.93
    安い
    0.91
     Pov
    0.90
    Activations Density 0.003%

    No Known Activations