© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84331
    Prev
    Next
    INDEX
    Explanations

    consent to place cookies

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

    The neuron detects second-person directive or permission phrases (e.g. “if you want to…,” “you may…,” “report…to FDA”) that address the reader with instructions or calls to action.

    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
     acel
    -0.80
     diyor
    -0.79
    zedł
    -0.79
    miert
    -0.78
    стандарт
    -0.77
    umann
    -0.75
     symboles
    -0.75
     gober
    -0.73
     Tasmania
    -0.73
     suç
    -0.73
    POSITIVE LOGITS
     ihnen
    0.85
    ṳ
    0.84
    urbing
    0.83
    ihnachts
    0.82
    They
    0.81
    LTRB
    0.77
    opo
    0.76
    ɰ
    0.76
     your
    0.76
     них
    0.75
    Activations Density 0.012%

    No Known Activations