© 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. 115536
    Prev
    Next
    INDEX
    Explanations

    | filter or variable delimiter

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

    The neuron fires on various iteration or looping constructs in code (e.g. “ng-repeat”, “each”, “map”).

    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
     Lester
    -0.82
    otriz
    -0.77
     leps
    -0.76
     EVER
    -0.75
    неш
    -0.74
     altro
    -0.73
    paul
    -0.73
     ideje
    -0.71
     même
    -0.71
    iert
    -0.71
    POSITIVE LOGITS
     |
    3.14
    |
    2.92
     $|
    1.57
    }|
    1.49
    ∣
    1.46
    |\
    1.42
    ｜
    1.38
    |(
    1.38
    )|
    1.34
     $|\
    1.33
    Activations Density 0.100%

    No Known Activations