© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 94058
    Prev
    Next
    INDEX
    Explanations

    buoyancy and floating

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

    The neuron strongly activates on numeric tokens (digits or numbers) in the text.

    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
    ۞
    -0.77
    pergillus
    -0.69
    قدم
    -0.69
     ioutil
    -0.69
     मेरे
    -0.69
    Rails
    -0.68
    aconda
    -0.68
    fahan
    -0.66
     rumble
    -0.65
     психо
    -0.64
    POSITIVE LOGITS
     buoyancy
    3.09
     float
    2.84
     buoyant
    2.67
    float
    2.52
     floats
    2.50
     flotation
    2.41
    浮
    2.36
     Float
    2.19
    Float
    2.17
     floating
    2.17
    Activations Density 0.029%

    No Known Activations