© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3380
    Prev
    Next
    INDEX
    Explanations

    getting the last item

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

    This neuron fires most strongly on the shell‐style pipe operator and its surrounding commands (e.g. “dmesg | tail”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     first
    -1.50
     första
    -1.48
     pertama
    -1.45
     første
    -1.45
    แรก
    -1.34
     eerste
    -1.31
     ersten
    -1.24
    第一个
    -1.18
     הראשון
    -1.16
     начале
    -1.09
    POSITIVE LOGITS
     last
    4.34
     getLast
    3.20
    getLast
    3.09
    last
    3.05
    Last
    2.98
    最后一个
    2.98
     letzten
    2.92
     último
    2.89
     послед
    2.83
    最后
    2.78
    Activations Density 0.018%

    No Known Activations