© 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. 116164
    Prev
    Next
    INDEX
    Explanations

    potential clients, residents, buyers

    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
    Not in Any Lists

    No Comments

    Negative Logits
     will
    -0.07
    而在
    -0.06
     habrá
    -0.06
     started
    -0.06
     get
    -0.06
    ಿಸಿದ್ದರು
    -0.06
    льна
    -0.06
    acteria
    -0.06
     avrà
    -0.06
     शुरू
    -0.05
    POSITIVE LOGITS
     whichever
    0.07
     podľa
    0.07
     its
    0.07
     apabila
    0.06
     selon
    0.06
    if
    0.06
     jeśli
    0.06
     dle
    0.06
    according
    0.06
     möjligt
    0.06
    Activations Density 0.009%

    No Known Activations