© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103854
    Prev
    Next
    INDEX
    Explanations

    installed software

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

    the word "installed" in technical contexts about software installation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on mentions of installation, i.e. tokens related to “installed.”

    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
    y
    -3.36
    a
    -3.36
    e
    -2.97
    {
    -2.91
    u
    -2.77
     élevés
    -2.69
    k
    -2.48
    ा
    -2.31
    t
    -2.23
    o
    -2.23
    POSITIVE LOGITS
     любых
    2.30
     generando
    2.23
     installed
    2.17
    木製
    2.17
    ፨
    2.09
    衪
    2.09
    ならない
    2.05
    ⢅
    2.05
     recientemente
    2.00
     newest
    1.99
    Activations Density 0.008%

    No Known Activations