© 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. 50255
    Prev
    Next
    INDEX
    Explanations

    programming languages and functions

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

    This neuron responds strongly to language‐provided APIs and constructors (built-in functions or classes) such as parseInt, RegExp, Buffer, MIMEApplication, 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_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
    ふわ
    -0.79
     саме
    -0.79
     ErrIntOverflow
    -0.79
    そのような
    -0.78
     dette
    -0.77
    Там
    -0.75
     debería
    -0.75
     diagon
    -0.73
     indol
    -0.73
     confortable
    -0.72
    POSITIVE LOGITS
    möglichen
    0.84
    ماني
    0.83
    ')}}"
    0.83
    )‏
    0.83
    ``,
    0.82
    』、
    0.81
    requestBody
    0.79
    ṉ
    0.79
    ++,
    0.79
    inä
    0.78
    Activations Density 0.056%

    No Known Activations