© 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. 81151
    Prev
    Next
    INDEX
    Explanations

    start of specific entries or headings

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

    The neuron is specialized to pick out numeric literals (i.e. number tokens) in source code.

    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
    westen
    -0.82
    新建
    -0.81
    BASEPATH
    -0.80
    lunda
    -0.77
     occidentalis
    -0.77
     Sei
    -0.76
     embry
    -0.75
     Produtos
    -0.75
     denomin
    -0.74
    assertNotNull
    -0.74
    POSITIVE LOGITS
     internal
    1.86
     external
    1.53
    internal
    1.32
     public
    1.29
     wewnętr
    1.16
    public
    1.05
    内部
    1.04
     internally
    1.02
     interno
    1.02
     внутренней
    0.99
    Activations Density 0.003%

    No Known Activations