© 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. 83756
    Prev
    Next
    INDEX
    Explanations

    data schema definitions

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

    The neuron specifically detects the token “schema” (i.e. occurrences of the word or substring “schema” in code or config).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    熥
    -2.80
    ︕
    -2.77
     GOtt
    -2.73
    訁
    -2.70
    埽
    -2.66
    鐿
    -2.63
    栊
    -2.59
    }
    -2.55
    ского
    -2.53
    就像是
    -2.52
    POSITIVE LOGITS
    內的
    2.52
     deberán
    2.25
     tendrán
    2.19
    
    2.17
    ൎ
    2.13
     неда
    2.09
     aksesuar
    2.06
     aseg
    2.06
    Ꭽ
    2.06
    ありますが
    2.05
    Activations Density 0.012%

    No Known Activations