© 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. 39529
    Prev
    Next
    INDEX
    Explanations

    programming code keywords

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

    The neuron fires on long runs of space characters—i.e. indentation whitespace.

    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
     not
    -2.11
     all
    -1.87
     their
    -1.83
     both
    -1.80
     its
    -1.80
     most
    -1.66
     three
    -1.60
     now
    -1.58
     this
    -1.57
     two
    -1.57
    POSITIVE LOGITS
     パッド
    1.52
     weihnachten
    1.46
     schuhe
    1.44
    küche
    1.43
     💕
    1.36
     figliu
    1.36
     CURRENT
    1.35
    schuhe
    1.33
     Dinas
    1.30
     moron
    1.30
    Activations Density 0.003%

    No Known Activations