© 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. 34-GEMMASCOPE-RES-131K
    7. 75536
    Prev
    Next
    INDEX
    Explanations

    binary search and programming

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

    The neuron is triggered by C‐style integer code—spots like “int,” numeric literals, and integer comparisons or arithmetic operators.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    SceneManagement
    -0.89
    خلا
    -0.76
    बाह
    -0.75
    weakSelf
    -0.73
    小学生
    -0.72
    ryu
    -0.72
    zás
    -0.70
     contador
    -0.69
     ud
    -0.69
    énario
    -0.69
    POSITIVE LOGITS
     search
    1.76
     bisect
    1.63
     Search
    1.52
    Search
    1.38
     searches
    1.31
    bise
    1.30
     searching
    1.30
    search
    1.28
     SEARCH
    1.24
     searched
    1.23
    Activations Density 0.022%

    No Known Activations