© 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. 386
    Prev
    Next
    INDEX
    Explanations

    policy and restrictions

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

    The neuron fires on boilerplate legal/license text—i.e. the formal wording and keywords you find in software licenses, notices, and official policy headers.

    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
     there
    -1.00
     then
    -0.92
     that
    -0.89
     chose
    -0.85
     quần
    -0.84
     through
    -0.81
     same
    -0.81
     have
    -0.79
     choose
    -0.78
    Aquatic
    -0.78
    POSITIVE LOGITS
     supersede
    1.13
     super
    1.10
    iosa
    0.97
    YSIS
    0.96
    super
    0.96
     shall
    0.95
     replaces
    0.94
     Strada
    0.94
     inoltre
    0.94
     superseded
    0.92
    Activations Density 0.049%

    No Known Activations