© 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. 22-GEMMASCOPE-RES-131K
    7. 32729
    Prev
    Next
    INDEX
    Explanations

    drive shafts transferring power

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

    The neuron fires on code‐specific identifiers—things like class names, API calls, resource references, and other programming tokens.

    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
     banheiro
    -1.15
     botas
    -1.10
     those
    -1.08
     escritório
    -1.04
     morada
    -1.03
     metais
    -1.02
    Ostat
    -1.02
     jornal
    -0.98
    Ꮔ
    -0.98
     berbahaya
    -0.97
    POSITIVE LOGITS
     '',
    1.01
    比起
    0.98
    研究生
    0.95
     pioneers
    0.95
    ⅓
    0.94
     "",
    0.93
     impermeable
    0.93
    guous
    0.90
    ⅕
    0.89
    ()<
    0.86
    Activations Density 0.000%

    No Known Activations