© 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. 63883
    Prev
    Next
    INDEX
    Explanations

    highest priority

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

    The neuron specializes in spotting language that marks something as a primary focus or top priority (e.g. “priority,” “top priority,” “primary concern,” “safety,” “important”).

    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
    Forrás
    -0.85
    ěji
    -0.84
    注定
    -0.83
     ĝ
    -0.81
    recommended
    -0.81
    jst
    -0.80
    Ŏ
    -0.80
    Ᏻ
    -0.79
     favorita
    -0.79
    gemene
    -0.79
    POSITIVE LOGITS
     priority
    4.56
    priority
    3.36
     Priority
    2.98
    Priority
    2.97
     priorities
    2.86
     приорите
    2.63
     prioridad
    2.50
     priorité
    2.45
    PRIORITY
    2.28
    优先
    2.23
    Activations Density 0.041%

    No Known Activations