© 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. 22-GEMMASCOPE-RES-131K
    7. 129327
    Prev
    Next
    INDEX
    Explanations

    This neuron primarily activates on numeric literals (and their assignments) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    introduction to Minnesota State Highway

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     シャツ
    -0.94
    ご了承
    -0.91
     catto
    -0.89
     tipe
    -0.88
     ブラウス
    -0.87
    nelse
    -0.86
     membership
    -0.82
    mmHg
    -0.82
     mouseClicked
    -0.81
     昭和
    -0.80
    POSITIVE LOGITS
    Contributors
    0.91
    的结果
    0.90
     Shy
    0.85
     onlar
    0.85
     oaths
    0.84
    IANA
    0.84
     Fundraising
    0.83
    Shy
    0.81
     grooved
    0.81
     hugs
    0.79
    Activations Density 0.003%

    No Known Activations