© 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. 10-GEMMASCOPE-RES-131K
    7. 57571
    Prev
    Next
    INDEX
    Explanations

    measurement per instance

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

    The main thing this neuron does is detect numeric measurements and counts (e.g. quantities with units or “per”‐style data points) in scientific contexts.

    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
    但他
    -1.59
    但她
    -1.42
      
    -1.39
    ſche
    -1.34
     بسبب
    -1.31
     moſt
    -1.29
     probleem
    -1.29
     reager
    -1.27
    糴
    -1.24
     maart
    -1.23
    POSITIVE LOGITS
     this
    1.84
     including
    1.69
    including
    1.63
     Including
    1.52
    на
    1.47
     There
    1.46
    ра
    1.46
     Sehingga
    1.40
     contextLoads
    1.40
     Vereinig
    1.37
    Activations Density 0.029%

    No Known Activations