© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 15263
    Prev
    Next
    INDEX
    Explanations

    Vue.js directives and attributes

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

    The neuron fires on numeric literals (numbers, including integers and floats) in the 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_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
    出了一
    -1.60
     kanskje
    -1.55
    倧
    -1.49
     نباید
    -1.48
    ContentAsync
    -1.47
    ');
    -1.44
    就连
    -1.44
     veldig
    -1.43
    ggish
    -1.43
    `,
    
    -1.40
    POSITIVE LOGITS
    ay
    1.68
     the
    1.54
    a
    1.50
    ed
    1.45
    i
    1.39
    u
    1.30
    校长
    1.29
    an
    1.28
     creativity
    1.27
    ai
    1.27
    Activations Density 0.022%

    No Known Activations