© 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. 130610
    Prev
    Next
    INDEX
    Explanations

    cross-section area

    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
     नस्
    -0.07
    àng
    -0.06
    even
    -0.06
     निघ
    -0.06
     সেখান
    -0.06
     등에
    -0.06
    ancake
    -0.06
    कहां
    -0.06
     Technische
    -0.06
     ঘুর
    -0.06
    POSITIVE LOGITS
    擁有
    0.06
     grueso
    0.06
    拥有
    0.06
     ủy
    0.06
     தற்போது
    0.06
     bosques
    0.06
    टेन
    0.06
    Nearly
    0.06
     audiences
    0.06
    Do
    0.06
    Activations Density 0.002%

    No Known Activations