© 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. 116990
    Prev
    Next
    INDEX
    Explanations

    majority

    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
     kunnen
    -0.07
     abdomen
    -0.06
     защото
    -0.06
     그것
    -0.06
    ładow
    -0.06
     quando
    -0.06
    የር
    -0.06
     вместо
    -0.06
     навіть
    -0.06
     abhängig
    -0.06
    POSITIVE LOGITS
     changed
    0.06
    elas
    0.06
    changed
    0.05
     Changed
    0.05
    DEBUG
    0.05
    Changed
    0.05
     Gar
    0.05
    точ
    0.05
    el
    0.05
     Tom
    0.05
    Activations Density 0.004%

    No Known Activations