© 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. 36060
    Prev
    Next
    INDEX
    Explanations

    about friday august

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

    The neuron fires on LaTeX‐style mathematical tokens—especially math identifiers like “SU” or “sigma” and matrix commands.

    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
    ющи
    -1.06
    Și
    -1.06
     of
    -1.06
     wszyst
    -1.00
     vulgaires
    -1.00
     citazioni
    -0.98
    hetically
    -0.94
    балан
    -0.94
    htub
    -0.94
     бампер
    -0.93
    POSITIVE LOGITS
    ῷ
    1.22
     people
    1.13
     fierce
    1.02
     bosque
    1.00
     hungry
    1.00
    Filmography
    0.98
    档案馆
    0.94
     אחרים
    0.94
     sorprendente
    0.93
    家乡
    0.93
    Activations Density 0.004%

    No Known Activations