© 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. 22-GEMMASCOPE-RES-131K
    7. 95328
    Prev
    Next
    INDEX
    Explanations

    recent past events

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

    The neuron strongly activates on quantitative expressions—numbers, counts, measurements, and related statistical 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_22/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
     still
    -1.58
     was
    -1.51
     first
    -1.24
     knew
    -1.16
     did
    -1.16
     immediately
    -1.16
     gave
    -1.15
     fjor
    -1.10
    āja
    -1.09
    最初に
    -1.09
    POSITIVE LOGITS
     since
    3.28
     lately
    2.66
    since
    2.33
     been
    2.30
     recently
    2.23
     recentemente
    2.14
     recientemente
    2.09
     SINCE
    2.08
     depuis
    2.03
    recently
    2.00
    Activations Density 0.476%

    No Known Activations