© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99432
    Prev
    Next
    INDEX
    Explanations

    ship hull and parts

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

    This neuron fires on technical terms naming boat propulsion, drive, hull, and marine equipment components.

    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
     Tenerife
    -0.87
     lata
    -0.84
     hacerlo
    -0.78
    Плюсы
    -0.78
     carat
    -0.77
    كتشاف
    -0.77
     uç
    -0.77
    Argumento
    -0.77
    WIND
    -0.77
    akyti
    -0.75
    POSITIVE LOGITS
     hull
    1.43
     underwater
    1.30
    hull
    1.13
     keel
    1.13
     rudder
    1.02
     bottom
    0.95
     trans
    0.94
    underwater
    0.91
     boot
    0.85
     Underwater
    0.85
    Activations Density 0.021%

    No Known Activations