© 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. 22-GEMMASCOPE-RES-131K
    7. 16074
    Prev
    Next
    INDEX
    Explanations

    presence, condition, or observation

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

    The neuron fires on words that occur in quantitative/measurement contexts—i.e. words immediately surrounding numeric values.

    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
     endgül
    -1.09
     another
    -1.01
     such
    -0.92
     it
    -0.90
     can
    -0.87
    + 
    -0.86
     before
    -0.86
     could
    -0.85
    ándo
    -0.85
     or
    -0.82
    POSITIVE LOGITS
     наличии
    0.96
     überhaupt
    0.95
     наличие
    0.94
    の種類
    0.94
    り物
    0.93
    ंप
    0.93
    equipped
    0.92
     varier
    0.91
     тях
    0.90
    oluble
    0.90
    Activations Density 0.205%

    No Known Activations