© 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. 10-GEMMASCOPE-RES-131K
    4. 9767
    Prev
    Next
    INDEX
    Explanations

    C/C++ standard library includes

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

    This neuron detects C/C++ `#include` directives, specifically the header‐file names (e.g. stdio, stdlib, string, unistd, etc.).

    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
     or
    -1.56
    hijab
    -1.53
    valentino
    -1.46
    pantal
    -1.44
    gilet
    -1.43
     considérée
    -1.40
    mieszkanie
    -1.38
     volledig
    -1.38
     ними
    -1.35
    cyjny
    -1.35
    POSITIVE LOGITS
    .
    2.17
     with
    1.81
    iyle
    1.42
     back
    1.40
    When
    1.39
    </em>
    1.39
     industriale
    1.34
    Unlike
    1.30
    Also
    1.29
    を開催
    1.28
    Activations Density 0.039%

    No Known Activations