© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67082
    Prev
    Next
    INDEX
    Explanations

    assignment of variables

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

    The neuron fires on the “=” symbol, spotting equality or assignment operators in formulas and code.

    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
    ｋ
    -1.22
     sowohl
    -1.19
     vermutlich
    -1.16
     Ikke
    -1.09
     When
    -1.07
     Problemen
    -1.06
    ETRIC
    -1.04
     aree
    -1.03
    その
    -1.02
    CRIPTION
    -1.02
    POSITIVE LOGITS
     =
    1.19
    就行
    1.06
    就行了
    1.05
     クッキー
    1.03
    で大
    1.02
    就可以了
    1.02
    .
    1.02
    uteurs
    1.01
    以免
    1.00
    性を
    0.99
    Activations Density 0.007%

    No Known Activations