© 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. 34-GEMMASCOPE-RES-131K
    7. 31201
    Prev
    Next
    INDEX
    Explanations

    mathematical and code expressions

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

    The neuron fires on standalone mathematical identifiers (single‐ or multi‐letter variable names like A, B, G, X, AC, y, v, etc.) used in formulas.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    為に
    -1.05
     betyr
    -1.04
     Tài
    -1.02
     sería
    -1.01
     چیست
    -1.00
    :
    -0.99
    ajemy
    -0.98
     çünkü
    -0.98
     Màu
    -0.97
     pensó
    -0.97
    POSITIVE LOGITS
    Comentários
    1.22
     aspi
    1.19
    ジナル
    1.11
    Composição
    1.10
    Crítica
    1.06
     vaid
    1.06
    душка
    1.04
     then
    1.03
    しますが
    1.02
    Procedimento
    1.02
    Activations Density 0.004%

    No Known Activations