© 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. 15849
    Prev
    Next
    INDEX
    Explanations

    security scheme

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

    This neuron detects Spring (Boot/Cloud) configuration property names and their dot-delimited segments.

    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
     Beobachtungen
    -1.41
    utant
    -1.40
     Bemerkungen
    -1.38
    hattan
    -1.35
     correc
    -1.33
    quitos
    -1.29
     avowed
    -1.28
     whom
    -1.28
    omel
    -1.28
     Anzeigen
    -1.26
    POSITIVE LOGITS
     neum
    1.27
     all
    1.21
     bawa
    1.20
     eius
    1.18
     marcos
    1.16
     with
    1.16
    ↵
    1.16
     nostru
    1.16
    什么的
    1.14
     musica
    1.13
    Activations Density 0.037%

    No Known Activations