© 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. 120515
    Prev
    Next
    INDEX
    Explanations

    BIO HAZARD

    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
     Some
    -0.07
     When
    -0.07
     These
    -0.07
     Taking
    -0.06
     The
    -0.06
     If
    -0.06
     Take
    -0.06
    ご連絡
    -0.06
    Previous
    -0.06
     This
    -0.06
    POSITIVE LOGITS
     கிஷ
    0.06
     preferências
    0.06
     notoriously
    0.06
     estimado
    0.06
     preferencias
    0.06
    LIMIT
    0.06
     antena
    0.06
    㔹
    0.06
     начинается
    0.06
     belongings
    0.06
    Activations Density 0.009%

    No Known Activations