© 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. 10-GEMMASCOPE-RES-131K
    7. 71996
    Prev
    Next
    INDEX
    Explanations

    PAN, Chico

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

    This neuron is tracking each token’s absolute position in the document.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    呖
    -3.47
     ſou
    -2.94
    歘
    -2.67
    🧌
    -2.67
    昻
    -2.56
    鰾
    -2.53
    ل
    -2.52
     usamos
    -2.48
    镚
    -2.45
    咵
    -2.38
    POSITIVE LOGITS
    Since
    2.98
    When
    2.61
    м
    2.56
    Everything
    2.47
    This
    2.44
    Unlike
    2.41
    Once
    2.38
    During
    2.38
    Because
    2.38
    Most
    2.38
    Activations Density 0.010%

    No Known Activations