© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128153
    Prev
    Next
    INDEX
    Explanations

    This neuron flags specialized technical or scientific jargon—particularly long, domain‐specific nouns and verbs (e.g. words ending in –ion, –ive, –cts, or acronyms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    URL and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     through
    -1.14
    的重要性
    -1.01
    Having
    -0.98
    人们
    -0.94
    cleos
    -0.93
     popoli
    -0.93
     曾
    -0.91
     melalui
    -0.90
     tamen
    -0.89
     verbund
    -0.88
    POSITIVE LOGITS
    <bos>
    0.98
     потому
    0.89
     reality
    0.87
    ťou
    0.87
    大哥
    0.86
     nô
    0.86
     done
    0.86
    acyjnych
    0.86
     we
    0.85
     deinen
    0.85
    Activations Density 0.184%

    No Known Activations