© 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. 22-GEMMASCOPE-RES-131K
    7. 26499
    Prev
    Next
    INDEX
    Explanations

    documents, requirements, and orders

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

    The neuron fires on procedural and administrative keywords—terms that signal steps or formal actions (e.g. plan, process, requirements, order).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    見えます
    -0.94
     largely
    -0.92
    vedev
    -0.86
     nabízí
    -0.86
     Zeitraum
    -0.85
     admittedly
    -0.85
     kunnen
    -0.83
    Faça
    -0.83
     coś
    -0.82
    ejemplo
    -0.81
    POSITIVE LOGITS
     preparations
    1.02
     Januari
    0.98
    🤓
    0.97
    😡
    0.95
    🤬
    0.94
    etta
    0.93
     Februari
    0.91
    😒
    0.91
    🤠
    0.91
    🤡
    0.90
    Activations Density 0.067%

    No Known Activations