© 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. 34-GEMMASCOPE-RES-131K
    7. 116765
    Prev
    Next
    INDEX
    Explanations

    in or inside

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

    This neuron lights up on content‐rich, uncommon words—especially proper names and specific nouns—while ignoring common function 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_34/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
     energías
    -1.09
     cálido
    -0.96
     diámetro
    -0.94
     bewertet
    -0.93
     cualidades
    -0.93
     cubiertas
    -0.91
     excelencia
    -0.90
     exportación
    -0.88
     присут
    -0.88
    ここで
    -0.88
    POSITIVE LOGITS
     in
    4.25
     într
    1.76
     dalam
    1.69
     housed
    1.65
     σε
    1.52
    อยู่ใน
    1.48
     inside
    1.40
     contained
    1.39
    在一个
    1.35
    ใน
    1.34
    Activations Density 0.128%

    No Known Activations