© 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. 119210
    Prev
    Next
    INDEX
    Explanations

    growing conditions, food quality, amino acids, age post mortem

    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
     production
    -0.07
     पैदा
    -0.06
    production
    -0.06
    تاج
    -0.06
     оптими
    -0.06
     putea
    -0.06
     உற்பத்தி
    -0.06
     lakini
    -0.06
     exuberant
    -0.06
     producing
    -0.06
    POSITIVE LOGITS
     нашим
    0.06
    нти
    0.06
     spot
    0.06
     неба
    0.06
    afety
    0.06
     variously
    0.06
    ल्ली
    0.06
     स्था
    0.05
    plings
    0.05
     സ്ത്രീ
    0.05
    Activations Density 0.019%

    No Known Activations