© 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. 10-GEMMASCOPE-RES-131K
    7. 65627
    Prev
    Next
    INDEX
    Explanations

    C/C++ macro definitions

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

    The neuron fires primarily on numeric constants (including digits within macros, literals, and parenthesized numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    tedrale
    -1.41
    cznej
    -1.38
    </strong>
    -1.34
     صلى
    -1.33
    You
    -1.31
    amentos
    -1.30
    They
    -1.28
     (!__
    -1.28
    (!__
    -1.27
     آن‌ها
    -1.27
    POSITIVE LOGITS
     our
    1.62
    战术
    1.52
     inalámb
    1.50
     we
    1.48
     justamente
    1.47
     ganó
    1.44
    这样一个
    1.44
    aabb
    1.40
     myös
    1.36
     anuales
    1.36
    Activations Density 0.020%

    No Known Activations