© 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. 10-GEMMASCOPE-RES-131K
    4. 87006
    Prev
    Next
    INDEX
    Explanations

    sizes and engine displacement

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

    The neuron primarily detects numeric measurement tokens—numbers (often with decimal points) that specify quantities such as engine displacement, horsepower, dimensions, and other technical specs.

    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
    łaści
    -1.27
    jados
    -1.20
    örper
    -1.20
     like
    -1.19
     robus
    -1.16
    bufio
    -1.13
     generali
    -1.12
    basically
    -1.11
    specifically
    -1.11
    磔
    -1.09
    POSITIVE LOGITS
     only
    1.30
     peligroso
    1.26
     size
    1.24
     that
    1.24
     srd
    1.21
     только
    1.20
    ometrica
    1.20
     erzielen
    1.20
     sizes
    1.19
     LOVE
    1.19
    Activations Density 0.072%

    No Known Activations