© 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. 68496
    Prev
    Next
    INDEX
    Explanations

    investigation, police, crime, Mueller

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

    The neuron detects mentions of law-enforcement or investigative agencies by name or acronym.

    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
    ﹣
    -1.38
    harapkan
    -1.34
     barcos
    -1.34
    潾
    -1.30
     gritos
    -1.28
     ℃
    -1.27
     engelsk
    -1.27
     landmarks
    -1.26
    dicionado
    -1.22
     ڤ
    -1.21
    POSITIVE LOGITS
     him
    1.24
    ？』
    1.21
     have
    1.20
     it
    1.19
    columnHeader
    1.18
    ing
    1.16
     in
    1.14
     całego
    1.13
     of
    1.12
     aquello
    1.11
    Activations Density 0.046%

    No Known Activations