© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63472
    Prev
    Next
    INDEX
    Explanations

    centering and tables

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

    The neuron flags tokens that introduce or mark code/markup constructs (e.g. comment delimiters, XML processing instructions, LaTeX backslashes, environment names, package keywords).

    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
     Harga
    -0.77
    ≳
    -0.77
     بهد
    -0.75
    greetings
    -0.75
     التش
    -0.74
    andan
    -0.73
     vlieg
    -0.73
    royd
    -0.73
     gouden
    -0.73
     занятия
    -0.73
    POSITIVE LOGITS
     centrum
    1.28
     table
    1.16
     Table
    1.13
     Center
    1.12
     center
    1.05
    Table
    1.02
     цент
    1.00
     central
    0.98
     Centre
    0.98
    centerTitle
    0.95
    Activations Density 0.001%

    No Known Activations