© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 32631
    Prev
    Next
    INDEX
    Explanations

    `for` loop iterations

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

    This neuron activates on numeric literals (numbers) in the code.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     and
    -1.75
     of
    -1.20
     for
    -1.13
     from
    -1.11
     but
    -1.05
    了一些
    -1.00
     among
    -0.96
     by
    -0.94
     or
    -0.84
    inosi
    -0.84
    POSITIVE LOGITS
     forsø
    1.00
    今回は
    0.96
    私の
    0.94
    自分の
    0.93
     $\}$
    0.93
    strando
    0.93
     intégral
    0.92
    私は
    0.92
    によって
    0.91
    نامج
    0.90
    Activations Density 0.006%

    No Known Activations