© 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. 45656
    Prev
    Next
    INDEX
    Explanations

    certificates and qualifications

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

    The neuron primarily detects numeric tokens such as dates, years, and other numbers.

    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
    <0xE1>
    -0.82
    トゥ
    -0.78
    萦
    -0.75
     Pah
    -0.74
     unten
    -0.74
    粲
    -0.73
    𝐌
    -0.71
    Спасылкі
    -0.69
     semillas
    -0.69
    ⇄
    -0.66
    POSITIVE LOGITS
     qualification
    1.77
     qualifications
    1.64
     Level
    1.44
     certificate
    1.41
     certificates
    1.31
     Certificate
    1.23
     level
    1.16
    Level
    1.13
     LEVEL
    1.12
    Qualifications
    1.11
    Activations Density 0.018%

    No Known Activations