© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21391
    Prev
    Next
    INDEX
    Explanations

    long haul movement

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

    The neuron strongly activates on the stem “haul” in words (e.g. haul, hauling, hauled, long-haul), i.e. it detects mentions of hauling or long-distance transport.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ”،
    -2.42
    
    -2.39
     Which
    -2.28
     berättar
    -2.27
     RSITY
    -2.25
    ة
    -2.23
     ところ
    -2.20
     raises
    -2.20
     髪型
    -2.20
    which
    -2.19
    POSITIVE LOGITS
    ную
    2.72
     arkas
    2.45
     комнате
    2.45
     haul
    2.38
    内心
    2.33
    珵
    2.30
     menac
    2.28
    said
    2.27
    ケモン
    2.22
    ным
    2.20
    Activations Density 0.002%

    No Known Activations