© 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. 73367
    Prev
    Next
    INDEX
    Explanations

    compound modifiers

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

    The neuron strongly activates on numeric or quantitative tokens (e.g. numbers, numeric measurements, or data 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
    蒾
    -1.30
    istorante
    -1.28
    yyj
    -1.26
    Gön
    -1.26
    🧏
    -1.25
    都已经
    -1.23
     guerras
    -1.23
     anunció
    -1.23
    Mvh
    -1.22
    zzet
    -1.21
    POSITIVE LOGITS
    -
    1.45
     is
    1.36
     should
    1.30
     (
    1.30
      
    1.26
     may
    1.26
     could
    1.23
       
    1.23
    2
    1.22
     -
    1.21
    Activations Density 0.176%

    No Known Activations