© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31818
    Prev
    Next
    INDEX
    Explanations

    settings and parameters

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

    The neuron specializes in spotting imperative command verbs – the “do this next” action words that start procedural instructions.

    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
    ARROLL
    -0.78
     thermometers
    -0.72
    Externé
    -0.71
    ución
    -0.71
    imensional
    -0.69
    駄
    -0.69
    IActionResult
    -0.69
     院
    -0.68
    шні
    -0.68
    zh
    -0.68
    POSITIVE LOGITS
     settings
    4.34
     setting
    3.69
    settings
    3.34
     Settings
    3.05
    Settings
    2.92
    Setting
    2.83
    setting
    2.77
    SETTINGS
    2.73
     Setting
    2.70
    設定
    2.47
    Activations Density 0.036%

    No Known Activations