© 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. 24954
    Prev
    Next
    INDEX
    Explanations

    involving or with specific contexts

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

    The neuron is simply tracking the absolute token position in the input (i.e. the index of each token within the document).

    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
     miniatura
    -0.96
    ähig
    -0.96
     commer
    -0.96
    隐藏
    -0.95
    挑选
    -0.93
     أيضًا
    -0.92
    бражение
    -0.91
     ſu
    -0.91
     plaintext
    -0.91
     chacune
    -0.91
    POSITIVE LOGITS
     any
    1.62
     or
    1.55
     these
    1.52
     such
    1.48
     with
    1.47
     this
    1.27
     from
    1.23
     those
    1.23
     using
    1.16
     tersebut
    1.16
    Activations Density 0.133%

    No Known Activations