© 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. 128124
    Prev
    Next
    INDEX
    Explanations

    The neuron is triggered by mathematical or formulaic tokens—numbers, symbols, and terms used in equations or technical expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    abstract concepts and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ﾚ
    -1.00
    kiksi
    -0.90
    melen
    -0.90
    xiaomi
    -0.89
    genes
    -0.88
    闡
    -0.87
    mstyle
    -0.86
    ꪻ
    -0.86
    ilera
    -0.85
    出场
    -0.85
    POSITIVE LOGITS
     erila
    0.94
    ſt
    0.84
    ]")
    0.83
    munition
    0.82
     hence
    0.81
     mythic
    0.81
     instead
    0.81
    ഃ
    0.79
    という
    0.79
     Thế
    0.79
    Activations Density 0.075%

    No Known Activations