© 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. 117286
    Prev
    Next
    INDEX
    Explanations

    software and related

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

    This neuron fires on the initial summary block of a software listing (the product name, download count, sizes, and “most lightweight” summary), i.e. the metadata paragraph at the top of a software download description.

    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
    getC
    -0.86
     چوبی
    -0.81
    最後
    -0.79
     někdo
    -0.77
    ߏ
    -0.73
     booking
    -0.71
    册
    -0.71
    字体
    -0.70
     books
    -0.69
     datasets
    -0.69
    POSITIVE LOGITS
     Soft
    1.09
     software
    1.09
    Soft
    1.05
     Sof
    1.04
     SOFT
    1.02
    soft
    1.01
     sof
    0.98
     developer
    0.93
     program
    0.92
    SOFT
    0.91
    Activations Density 0.061%

    No Known Activations