© 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. 65685
    Prev
    Next
    INDEX
    Explanations

    final output of code statements

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

    The neuron is strongly triggered by numeric literals (sequences of digits) in code.

    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
    posables
    -1.02
     habari
    -1.02
    rekli
    -0.93
    telah
    -0.92
    sü
    -0.92
     می‌توانید
    -0.90
    昴
    -0.90
     kort
    -0.85
    虜
    -0.84
    ✮
    -0.84
    POSITIVE LOGITS
    最终
    1.21
    最后
    1.14
     uiteindelijk
    1.05
     final
    1.01
     eventually
    0.95
    最後は
    0.93
    最后的
    0.93
     النها
    0.89
    および
    0.88
    变成
    0.85
    Activations Density 0.006%

    No Known Activations