© 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. 128294
    Prev
    Next
    INDEX
    Explanations

    The neuron flags the main content-bearing technical or scholarly terms in academic‐style abstracts.

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

    introducing clauses and entities

    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
     you
    -2.45
     alemania
    -1.77
    Transk
    -1.70
     terbukti
    -1.69
    他有
    -1.64
    つづく
    -1.63
     your
    -1.55
    美国的
    -1.52
    辎
    -1.48
    versace
    -1.47
    POSITIVE LOGITS
    msgSender
    1.46
    UGH
    1.42
     jogos
    1.40
    ıt
    1.35
    เรา
    1.33
    न्दर्भ
    1.33
    Á
    1.31
    友人
    1.30
     Verwaltung
    1.28
    เป็น
    1.27
    Activations Density 0.008%

    No Known Activations