© 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. 64535
    Prev
    Next
    INDEX
    Explanations

    setting priorities

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

    The neuron fires on formal institutional or bureaucratic jargon—especially policy‐oriented action nouns (e.g. measurement, enforcement, governance, priorities).

    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
    pesan
    -0.88
     stiller
    -0.81
    bonsoir
    -0.79
    opsis
    -0.75
     كيف
    -0.74
     maquilla
    -0.74
    Hotels
    -0.73
    addContainer
    -0.73
    indahan
    -0.73
    endent
    -0.73
    POSITIVE LOGITS
     priorities
    5.75
     priority
    4.63
     Priorities
    4.25
    Priorities
    4.06
    priority
    3.95
    Priority
    3.72
     приорите
    3.69
     prioridades
    3.56
     Priority
    3.38
     prioriti
    3.22
    Activations Density 0.045%

    No Known Activations