© 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. 117620
    Prev
    Next
    INDEX
    Explanations

    thermal physics and phase transitions

    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
     figured
    -0.06
     redes
    -0.06
     Dams
    -0.06
     saldo
    -0.06
     Exhibit
    -0.06
     pests
    -0.06
     gewann
    -0.06
     dopiero
    -0.06
     toxicity
    -0.06
     sculptural
    -0.06
    POSITIVE LOGITS
    秉
    0.06
    6
    0.06
    OVERRIDES
    0.06
    8
    0.06
    fromString
    0.06
     воспомина
    0.05
     آز
    0.05
    𝙶
    0.05
     kT
    0.05
     खरीद
    0.05
    Activations Density 0.006%

    No Known Activations