© 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. 104587
    Prev
    Next
    INDEX
    Explanations

    code special characters and operators

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

    C++ operator overloading syntax, particularly the opening parenthesis after the operator keyword.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on C++ operator overload declarations (e.g. definitions of operator<<, operator>>, operator<, operator==).

    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
     
    -1.53
    AFTER
    -1.53
    行った
    -1.49
    ܆
    -1.43
    进入了
    -1.41
    first
    -1.40
     problemet
    -1.39
    漂亮的
    -1.35
    basically
    -1.34
    —–
    -1.33
    POSITIVE LOGITS
     on
    2.09
     at
    1.99
    droj
    1.77
     for
    1.68
    学期
    1.66
     शुर
    1.58
     of
    1.54
     упаковка
    1.53
     young
    1.53
    replyreport
    1.50
    Activations Density 0.004%

    No Known Activations