© 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. 22-GEMMASCOPE-RES-131K
    4. 67400
    Prev
    Next
    INDEX
    Explanations

    issue numbers and dates

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

    The neuron responds to numeric tokens—especially digits in version numbers, issue or bug IDs, and other code‐related numeric references.

    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
    と思っている
    -1.17
    洐
    -1.15
     use
    -1.12
    って思
    -1.11
    xlarge
    -1.04
    itanie
    -1.03
    出来ました
    -1.03
    ностей
    -1.02
     in
    -1.02
    片刻
    -1.02
    POSITIVE LOGITS
     mivel
    1.14
     oluyor
    1.09
    の時
    1.09
     ARISING
    1.02
    forderungen
    1.02
    マジで
    1.01
     precies
    1.00
    футболка
    0.98
     り
    0.96
    machen
    0.96
    Activations Density 0.018%

    No Known Activations