© 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. 70055
    Prev
    Next
    INDEX
    Explanations

    statistical analysis terms

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

    The neuron detects numeric tokens—i.e. numbers and numeric results—throughout 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_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
     observado
    -0.93
     soggetti
    -0.93
     correlated
    -0.92
     instruk
    -0.92
     ανθρώ
    -0.88
     koncep
    -0.88
     fattori
    -0.88
    غرب
    -0.88
     misma
    -0.85
     princesas
    -0.84
    POSITIVE LOGITS
     test
    1.34
     tests
    1.20
     was
    1.16
    tests
    1.15
     procedure
    1.15
     testing
    1.12
    testing
    1.09
    test
    1.05
     теста
    1.02
     analysis
    1.00
    Activations Density 0.087%

    No Known Activations