© 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. 65239
    Prev
    Next
    INDEX
    Explanations

    grammar and technical terms

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

    The neuron responds to relatively long or specialized content tokens—especially technical terms, rare jargon, or uncommon multi-syllable words.

    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
    čni
    -1.20
    ཥ
    -1.13
    
    -1.11
    ſten
    -1.10
    粝
    -1.06
     zowel
    -1.02
    CZE
    -1.02
    Елена
    -1.02
    Мон
    -0.94
    脔
    -0.94
    POSITIVE LOGITS
     after
    1.16
     February
    1.15
    ？！”
    1.09
     October
    1.06
     if
    1.05
     it
    1.05
     by
    1.02
     December
    1.02
     has
    1.01
     one
    1.01
    Activations Density 0.065%

    No Known Activations