© 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. 57077
    Prev
    Next
    INDEX
    Explanations

    software installers and installation

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

    The neuron is triggered by numeric tokens—especially software version numbers and other digit sequences.

    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
    neem
    -0.70
    Writing
    -0.69
    Judge
    -0.69
     pertandingan
    -0.68
    flexDirection
    -0.67
     relacion
    -0.67
    writing
    -0.67
    ungkinkan
    -0.67
    헤
    -0.66
     Američ
    -0.66
    POSITIVE LOGITS
     installer
    2.97
     installers
    2.52
    installer
    2.22
     Installer
    2.13
     installation
    2.13
    Installer
    2.02
    Install
    1.80
     install
    1.80
     Install
    1.75
     setup
    1.66
    Activations Density 0.098%

    No Known Activations