© 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. 105559
    Prev
    Next
    INDEX
    Explanations

    measurement or reporting data

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

    The neuron strongly activates on technical research-methods vocabulary—especially words about measurement, instruments, outcomes, and related methodological terms.

    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
     that
    -2.89
     we
    -2.67
     our
    -2.17
     are
    -1.77
     previous
    -1.68
     then
    -1.64
    ,
    -1.53
     which
    -1.51
     current
    -1.48
    を行いました
    -1.45
    POSITIVE LOGITS
    ELTS
    1.45
     and
    1.38
    也
    1.32
     både
    1.30
     arī
    1.30
     in
    1.30
    在她
    1.27
     אינו
    1.27
     lahir
    1.25
    Moda
    1.25
    Activations Density 1.413%

    No Known Activations