© 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. 37792
    Prev
    Next
    INDEX
    Explanations

    ped prefix

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

    This neuron is detecting word prefixes "ped" or "pedi" (like pedometer, pedunculated, pedicle, peddling), with especially high activation for the first letters of these terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is specialized to detect the word “pedunculated” (i.e. the token sequence ped-un-culated).

    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
    orithmic
    -0.74
    сию
    -0.72
     nativo
    -0.72
    Autoritní
    -0.72
    kening
    -0.71
     dương
    -0.71
     उन
    -0.71
    销
    -0.71
     regular
    -0.70
    这就是
    -0.70
    POSITIVE LOGITS
     Ped
    1.54
     ped
    1.52
    Ped
    1.44
     PED
    1.06
    ped
    0.98
     Pedersen
    0.92
    uskas
    0.86
     oef
    0.85
    Zam
    0.84
    月から
    0.84
    Activations Density 0.014%

    No Known Activations