© 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. 22-GEMMASCOPE-RES-131K
    4. 95565
    Prev
    Next
    INDEX
    Explanations

    gem, package, dependencies

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

    This neuron detects references to Ruby gem installation and Gemfile (e.g. mentions of Gem, Gemfile, bundle install).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    [];
    
    -1.24
    $};
    -1.23
    羲
    -1.16
    æs
    -1.16
    --;
    
    -1.15
    lons
    -1.12
     with
    -1.10
    mener
    -1.10
    𝗼
    -1.09
    بوط
    -1.08
    POSITIVE LOGITS
     Eſ
    1.36
    tranh
    1.30
    quirer
    1.27
     rilev
    1.27
     пирог
    1.27
    tbx
    1.22
     caratteri
    1.21
     âge
    1.16
     rischi
    1.14
     télécharger
    1.13
    Activations Density 0.141%

    No Known Activations