© 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. 130145
    Prev
    Next
    INDEX
    Explanations

    j

    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
     سپس
    -0.06
     démontrer
    -0.06
     the
    -0.06
     episodes
    -0.06
    три
    -0.06
     reconstruction
    -0.06
     summits
    -0.05
    上有
    -0.05
     lorsque
    -0.05
    ак
    -0.05
    POSITIVE LOGITS
     suo
    0.07
     currant
    0.06
    とその
    0.06
     verschied
    0.06
    െന്ന
    0.06
     versatile
    0.05
     நன்ற
    0.05
    🏵
    0.05
    SERVICIO
    0.05
     служ
    0.05
    Activations Density 0.008%

    No Known Activations