© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 71654
    Prev
    Next
    INDEX
    Explanations

    united states of america

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

    The neuron fires on standalone identifier‐style tokens (e.g. API/class/type names like “FindWindow,” “Point,” “size,” etc.) 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
     with
    -1.47
     ihan
    -1.40
     from
    -1.38
     because
    -1.38
     áreas
    -1.34
     materiais
    -1.33
     ingredientes
    -1.30
     atau
    -1.30
     Desember
    -1.27
     και
    -1.25
    POSITIVE LOGITS
     betreffende
    1.36
    為に
    1.29
     hinzugefügt
    1.28
     wezen
    1.26
     frequentemente
    1.26
     normalerweise
    1.23
     erhi
    1.22
     aceste
    1.21
     lentamente
    1.17
     gewiß
    1.17
    Activations Density 0.000%

    No Known Activations