© 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. 10-GEMMASCOPE-RES-131K
    4. 127598
    Prev
    Next
    INDEX
    Explanations

    creatine kinase and pyruvate metabolism

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

    This neuron detects words related to containers, enclosures, or structural elements like "crated", "boxes", "cratons", and various technical terms.

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

    This neuron is detecting the character sequence “crat” (as found in tokens like crate, crated, craton, boxey/crate, etc.).

    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
    ne
    -2.81
    蜑
    -2.69
    鹩
    -2.64
    棪
    -2.64
    鹛
    -2.61
    횽
    -2.52
    dimensional
    -2.52
    the
    -2.50
    鹚
    -2.48
    綻
    -2.45
    POSITIVE LOGITS
     BOTH
    2.47
     *
    2.47
     
    2.39
     
    2.31
     otras
    2.31
     suas
    2.25
     similares
    2.23
    禿
    2.22
     suo
    2.22
     ‘
    2.17
    Activations Density 0.001%

    No Known Activations