© 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. 103048
    Prev
    Next
    INDEX
    Explanations

    compound nouns and political entities

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

    The neuron fires strongly on standalone numeric or identifier‐style tokens (e.g. version numbers, codes, standalone digits, file‐extension “.h” fragments).

    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
    君
    -0.82
     سری
    -0.70
    maßnahmen
    -0.68
     looted
    -0.68
    IW
    -0.68
     Warehouse
    -0.67
    tably
    -0.67
    guri
    -0.66
     Geschwindigkeit
    -0.65
     Numerology
    -0.64
    POSITIVE LOGITS
    istisch
    0.69
    maining
    0.68
    fromJson
    0.65
    setPixel
    0.65
     kaarangay
    0.65
     plu
    0.64
    resultSet
    0.63
     bon
    0.63
     Importance
    0.63
     bonfire
    0.63
    Activations Density 0.033%

    No Known Activations