© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117037
    Prev
    Next
    INDEX
    Explanations

    outpatient clinic or department

    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
    eszcze
    -0.06
     они
    -0.06
     mereka
    -0.06
     aún
    -0.06
     Besonder
    -0.06
    它们的
    -0.06
    后面的
    -0.06
     biasanya
    -0.06
     mediocre
    -0.06
     vacaciones
    -0.06
    POSITIVE LOGITS
     keeping
    0.07
     സംഭ
    0.06
     keeps
    0.06
     plotting
    0.06
     জার
    0.06
     Keeping
    0.05
     kept
    0.05
     our
    0.05
    Tick
    0.05
     প্রোডাক্ট
    0.05
    Activations Density 0.006%

    No Known Activations