© 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. 73866
    Prev
    Next
    INDEX
    Explanations

    your, you, Wife, Lap

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

    The neuron fires strongly on sentimental, affectionate expressions typical of greeting‐card language (declarations of love, friendship, and heartfelt praise).

    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
    וּ
    -1.50
    '>{
    -1.13
     Θε
    -1.12
    itively
    -1.12
    BindingResult
    -1.11
    Hermione
    -1.10
    DeclareMath
    -1.09
    ֶּ
    -1.06
     лука
    -1.06
    Jeho
    -1.06
    POSITIVE LOGITS
     your
    2.09
     you
    1.70
    上涨
    1.27
     النبات
    1.23
     eccl
    1.13
     фрук
    1.10
     totalité
    1.09
     always
    1.09
     ()
    1.09
     cheminée
    1.08
    Activations Density 0.010%

    No Known Activations