© 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. 10-GEMMASCOPE-RES-131K
    7. 70368
    Prev
    Next
    INDEX
    Explanations

    WordPress development terms

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

    The neuron is looking for programming identifiers—names of functions, hooks, variables, classes, and parameters—in code snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     afectadas
    -1.37
     คือ
    -1.32
    囮
    -1.31
    Idem
    -1.31
     alguns
    -1.31
    Ꮟ
    -1.30
     seleccionados
    -1.29
    
    -1.29
    IKit
    -1.27
     demikian
    -1.26
    POSITIVE LOGITS
     for
    1.59
     with
    1.42
    にぎり
    1.28
     then
    1.27
     forged
    1.25
     an
    1.24
    がありますが
    1.23
    R
    1.23
    ַּ
    1.23
     if
    1.23
    Activations Density 0.021%

    No Known Activations