© 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. 32676
    Prev
    Next
    INDEX
    Explanations

    code context and code identifiers

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

    This neuron responds to qualified column references in SQL (tokens like alias.field).

    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
     how
    -1.52
     etc
    -1.41
     what
    -1.24
     литера
    -1.09
    ╕
    -1.06
     fortale
    -1.05
     ۱۴۰۰
    -1.05
    sä
    -1.02
     methods
    -1.00
    odles
    -0.98
    POSITIVE LOGITS
     parfaite
    1.02
    ھے
    1.00
    ָּ
    0.98
    vskip
    0.98
     دے
    0.92
     snare
    0.92
    ̸
    0.92
     erhältlich
    0.92
     whirlpool
    0.91
    zzata
    0.91
    Activations Density 0.008%

    No Known Activations