© 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. 105196
    Prev
    Next
    INDEX
    Explanations

    create directory and set layout parameters

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

    the function or command `mkdir` (make directory) in code.

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

    The neuron activates on code identifiers that are function or method names (e.g. calls like executeQuery, mkdir, EventType).

    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
    5
    -2.39
    9
    -2.38
    на
    -2.34
     یا
    -2.33
     или
    -2.33
    1
    -2.22
    Even
    -2.08
    缃
    -2.03
     intrigue
    -2.02
    <>());
    -2.02
    POSITIVE LOGITS
    部分は
    2.61
    縞
    2.56
     “
    2.52
    ….”
    2.50
     небольшой
    2.45
     mejorando
    2.42
     
    2.42
    …”
    2.42
    晙
    2.41
    :”
    2.39
    Activations Density 0.003%

    No Known Activations