© 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. 103463
    Prev
    Next
    INDEX
    Explanations

    computational and technical terms

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

    The neuron is detecting chunks of Base64‐style (alphanumeric plus “+/”)-encoded data in the text.

    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
     its
    -0.92
     after
    -0.81
    واق
    -0.79
     Almost
    -0.79
     almost
    -0.79
     changes
    -0.79
     changed
    -0.79
     Even
    -0.77
    自ら
    -0.76
     Iranian
    -0.75
    POSITIVE LOGITS
    Sortable
    0.87
    CCION
    0.81
     Fide
    0.78
    Fingerprint
    0.78
    ξε
    0.78
     uti
    0.78
     Iš
    0.77
    Doubles
    0.77
    াব
    0.76
     nung
    0.76
    Activations Density 0.003%

    No Known Activations