© 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. 93209
    Prev
    Next
    INDEX
    Explanations

    javascript code syntax

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

    The neuron detects numeric literals (standalone numbers) in the text.

    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
     岁
    -0.96
    ต่างๆ
    -0.94
    ции
    -0.90
     gerak
    -0.88
    ↵↵
    -0.86
    .''
    -0.86
     eût
    -0.84
     prise
    -0.84
     Ľ
    -0.83
    ії
    -0.83
    POSITIVE LOGITS
     ส์
    1.09
     than
    0.98
    ###########
    0.98
    我也不
    0.98
    のではなく
    0.91
    므
    0.91
     बजाय
    0.90
     bereiken
    0.90
    mediated
    0.88
    cheibe
    0.88
    Activations Density 0.004%

    No Known Activations