© 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. 34-GEMMASCOPE-RES-131K
    7. 57177
    Prev
    Next
    INDEX
    Explanations

    drops and sprays

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

    The neuron strongly activates on numeric expressions and quantitative measurements (digits, counts, units).

    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
     scented
    -0.69
     Sprung
    -0.68
     powdered
    -0.67
     powder
    -0.66
     Scent
    -0.66
     میان
    -0.65
    漁港
    -0.65
    xbox
    -0.65
     airbag
    -0.65
    老师
    -0.65
    POSITIVE LOGITS
     drops
    1.59
     dropper
    1.43
    liquid
    1.32
    drops
    1.30
     Drops
    1.28
     bottle
    1.27
    Drops
    1.23
     liquid
    1.22
     dro
    1.16
     bottles
    1.12
    Activations Density 0.011%

    No Known Activations