© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118295
    Prev
    Next
    INDEX
    Explanations

    chronic energy deficiency

    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
     convened
    -0.07
    дения
    -0.06
    Historically
    -0.06
     какой
    -0.06
     Historically
    -0.06
     possível
    -0.06
    емого
    -0.06
     Founded
    -0.06
     angios
    -0.06
     luôn
    -0.06
    POSITIVE LOGITS
     部分
    0.07
     apresenta
    0.06
     liberties
    0.06
     spiega
    0.06
    ।
    0.06
     apresentam
    0.06
     safeguards
    0.05
     vade
    0.05
    structed
    0.05
    комиться
    0.05
    Activations Density 0.001%

    No Known Activations