© 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. 128976
    Prev
    Next
    INDEX
    Explanations

    base classes or general applicability

    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
     métodos
    -0.07
    Concerning
    -0.07
    ATIVA
    -0.06
     необходимо
    -0.06
     kebijakan
    -0.06
     mythology
    -0.06
     позволя
    -0.06
     operativos
    -0.06
     afbeelding
    -0.06
     listOf
    -0.06
    POSITIVE LOGITS
     all
    0.06
     everything
    0.06
     really
    0.06
    6
    0.06
    l
    0.06
    all
    0.06
     tudo
    0.05
     maybe
    0.05
     Science
    0.05
     उद
    0.05
    Activations Density 0.007%

    No Known Activations