© 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. 83627
    Prev
    Next
    INDEX
    Explanations

    Buffalo, Bradford and Pittsburgh Railroad

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

    The neuron fires on technical passages describing quantitative scientific metrics and units (e.g. measurement parameters in plant water‐status studies).

    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
    лиза
    -0.80
    ularia
    -0.80
    ﷼
    -0.79
    redire
    -0.74
    璜
    -0.73
    NoSuchAlgorithm
    -0.72
    cheiben
    -0.69
     administration
    -0.69
     formalin
    -0.68
    Keto
    -0.67
    POSITIVE LOGITS
     midday
    1.26
     thirsty
    1.14
     transpiration
    0.98
     water
    0.93
     thirst
    0.93
     Drought
    0.93
     morning
    0.91
     drought
    0.90
     воду
    0.90
     deficits
    0.90
    Activations Density 0.038%

    No Known Activations