© 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. 98026
    Prev
    Next
    INDEX
    Explanations

    numbers in scientific notation

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

    The neuron strongly activates on the “5” in serotonin receptor designations (e.g. the “5” in “5-HT1A” or “5-HT2C”), so it is detecting “5-HT” prefixes that denote serotonin receptor subtypes.

    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
     our
    -0.93
    Бил
    -0.92
     「
    -0.90
     lakier
    -0.89
     what
    -0.88
     many
    -0.88
     חיצוני
    -0.88
    aikan
    -0.88
     saltar
    -0.87
     all
    -0.86
    POSITIVE LOGITS
     تُ
    0.91
    ANA
    0.90
    hana
    0.89
     dotenv
    0.88
    uin
    0.88
    th
    0.88
     liknande
    0.86
     xxi
    0.85
    ENSE
    0.84
    ਡ
    0.84
    Activations Density 0.115%

    No Known Activations