© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130049
    Prev
    Next
    INDEX
    Explanations

    emergency responders and police actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     sorprendente
    -0.06
    IKI
    -0.06
     HEALTH
    -0.06
     contradicts
    -0.06
     shaky
    -0.06
     Surprisingly
    -0.06
    HEALTH
    -0.06
    宵
    -0.05
     feeble
    -0.05
     thumbnail
    -0.05
    POSITIVE LOGITS
    opathology
    0.07
     roadside
    0.07
     alanı
    0.07
    invest
    0.06
    周辺
    0.06
     cars
    0.06
    現場
    0.06
     Asphalt
    0.06
     hotspots
    0.06
     চারি
    0.06
    Activations Density 0.047%

    No Known Activations