© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39263
    Prev
    Next
    INDEX
    Explanations

    code, addresses, and programming terms

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

    The neuron is spot­ting address-related tokens—both “addr” identifiers (and variants) and address-of operators (the & operator) in 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
     manteiga
    -1.29
    蓠
    -1.27
    崀
    -1.21
    祤
    -1.20
     SPECIAL
    -1.17
     asume
    -1.16
    ⁛
    -1.16
     кнопки
    -1.15
     milho
    -1.15
    bex
    -1.14
    POSITIVE LOGITS
     when
    1.57
     was
    1.45
     at
    1.40
    ;
    1.35
     Although
    1.23
     how
    1.16
     in
    1.15
     for
    1.14
     bring
    1.14
     Despite
    1.13
    Activations Density 0.001%

    No Known Activations