© 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. 26245
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and notation

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

    The neuron activates on numeric expressions in math text—digits, fractions, ratios, and related numeric symbols.

    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
    maketitle
    -0.90
    requirements
    -0.88
    település
    -0.87
    ッシング
    -0.87
    ichts
    -0.85
    diferentes
    -0.81
     denunci
    -0.80
    lb
    -0.79
    Índice
    -0.79
    Reservation
    -0.79
    POSITIVE LOGITS
    errat
    0.89
     each
    0.85
    viedo
    0.85
     Each
    0.82
    每次
    0.79
    bigg
    0.77
    æa
    0.77
     vorne
    0.76
     distanza
    0.75
    อม
    0.74
    Activations Density 0.048%

    No Known Activations