© 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. 117851
    Prev
    Next
    INDEX
    Explanations

    single, only, simple, solo, completely

    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
     signif
    -0.06
     நிச்ச
    -0.06
    Hy
    -0.06
     derde
    -0.06
     хоть
    -0.06
     يش
    -0.06
    angat
    -0.06
     விழுப்புரம்
    -0.05
    thesis
    -0.05
    क्सीडेंट
    -0.05
    POSITIVE LOGITS
     locating
    0.06
     mois
    0.06
     there
    0.06
     ordinary
    0.06
     this
    0.06
     excav
    0.05
    安全
    0.05
     نہیں
    0.05
     alan
    0.05
    вичай
    0.05
    Activations Density 0.041%

    No Known Activations