© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93055
    Prev
    Next
    INDEX
    Explanations

    eval, evaluate, Eva

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

    The neuron activates on occurrences of the literal “eval,” i.e. instances where code is being evaluated or the eval function is used.

    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
    ARIES
    -0.81
    ığım
    -0.81
    NBT
    -0.79
    亡
    -0.79
    ὑ
    -0.79
    ANCY
    -0.77
    Convert
    -0.77
    ją
    -0.77
     تجمعات
    -0.76
     Dafür
    -0.75
    POSITIVE LOGITS
    ulate
    1.14
    ulation
    1.10
     Evalu
    1.03
    ulating
    1.02
    evalu
    0.96
    evaluated
    0.94
     evaluator
    0.92
    ulated
    0.88
    uated
    0.88
    ストレート
    0.87
    Activations Density 0.028%

    No Known Activations