© 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. 10-GEMMASCOPE-RES-131K
    7. 41523
    Prev
    Next
    INDEX
    Explanations

    questions and titles

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

    This neuron detects the block parameter “t” (the task object) in Rake task definitions when it’s used as a receiver (e.g. `t.options`, `t.files`).

    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
    -2.00
    7
    -1.95
    6
    -1.86
    4
    -1.79
    already
    -1.75
     ПРЕ
    -1.71
     gestartet
    -1.65
     préalable
    -1.64
     Características
    -1.63
    8
    -1.63
    POSITIVE LOGITS
     namor
    1.64
     such
    1.59
     شیپور
    1.58
     being
    1.56
     noiva
    1.53
     definitely
    1.52
    ционер
    1.52
    <td>
    1.52
     respira
    1.52
    </h2>
    1.48
    Activations Density 0.001%

    No Known Activations