© 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. 34-GEMMASCOPE-RES-131K
    7. 50069
    Prev
    Next
    INDEX
    Explanations

    policy and regulations

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

    The neuron fires on occurrences of the word “policy” (including in URL paths and titles).

    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
     appelez
    -0.85
     paciencia
    -0.82
    conven
    -0.79
     מס
    -0.76
    routed
    -0.75
    meas
    -0.73
     выгод
    -0.73
     заме
    -0.71
     hor
    -0.71
     confortável
    -0.70
    POSITIVE LOGITS
     reactant
    0.94
    _))
    0.78
     stubs
    0.78
     GAT
    0.78
     vento
    0.78
    ங
    0.77
     $)$
    0.75
    ӷ
    0.74
    ‟
    0.74
     spamming
    0.74
    Activations Density 0.035%

    No Known Activations