© 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. 26361
    Prev
    Next
    INDEX
    Explanations

    parameters of

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

    This neuron is detecting LaTeX‐style mathematical notation—especially curly braces (“{”) and embedded digits.

    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
     adjusts
    -0.84
     درمانی
    -0.82
     bounces
    -0.82
     листь
    -0.81
     absorbs
    -0.81
    異なる
    -0.81
    preso
    -0.81
     kampen
    -0.81
     продукти
    -0.81
     их
    -0.81
    POSITIVE LOGITS
     kto
    0.96
     comprimidos
    0.94
     territ
    0.94
    财政
    0.93
     ativ
    0.92
     nutricional
    0.92
    有些人
    0.89
    欤
    0.89
     procra
    0.88
     such
    0.87
    Activations Density 0.009%

    No Known Activations