© 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. 66455
    Prev
    Next
    INDEX
    Explanations

    verbs followed by related nouns

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

    The neuron flags numeric tokens, especially quantitative measurements, statistics, and other number values.

    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
     bambú
    -0.88
    osexuality
    -0.86
    some
    -0.84
     azok
    -0.84
     некоторых
    -0.84
     algumas
    -0.84
     wpły
    -0.84
     каких
    -0.83
    leyebilirsiniz
    -0.82
    Estamos
    -0.81
    POSITIVE LOGITS
    ‌های
    1.08
    es
    1.01
    ֶּ
    0.95
    們
    0.91
    citos
    0.90
     saben
    0.90
    tipos
    0.90
    쫓
    0.88
    ｓ
    0.88
    jes
    0.87
    Activations Density 0.320%

    No Known Activations