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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105711
    Prev
    Next
    INDEX
    Explanations

    software installation commands

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

    commands to install software packages, particularly using package managers like npm, gem, or yum.

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

    The neuron fires on package‐installation keywords and commands (e.g. “install,” “npm install,” “gem install,” version/download badges) indicating setup or install instructions.

    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
    ’
    -2.20
    ma
    -1.74
    _
    -1.71
     our
    -1.47
    ala
    -1.45
    any
    -1.42
    最后由
    -1.40
    unk
    -1.39
     наших
    -1.39
     ‘’
    -1.38
    POSITIVE LOGITS
    ꯶
    1.52
     деца
    1.47
    敺
    1.43
    !");
    1.41
     kecuali
    1.38
    красивые
    1.38
    --){
    1.37
    '];
    1.34
     жовтня
    1.34
    玧
    1.32
    Activations Density 0.040%

    No Known Activations