© 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. 127604
    Prev
    Next
    INDEX
    Explanations

    posterior anatomical locations

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

    The neuron detects the word "posterior" in medical and anatomical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron reliably detects occurrences of the word “posterior.”

    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
    ]."
    -2.39
    佉
    -2.23
    倌
    -2.23
    лением
    -2.22
    {//
    -2.17
     masses
    -2.17
    ्रीय
    -2.17
     .'
    -2.13
     marquee
    -2.09
     putri
    -2.06
    POSITIVE LOGITS
    This
    2.48
    the
    2.42
     And
    2.36
     Occasionally
    2.23
    in
    2.22
     Alternatively
    2.22
     должна
    2.20
    ஂ
    2.20
    いれば
    2.19
     From
    2.17
    Activations Density 0.004%

    No Known Activations