© 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. 119992
    Prev
    Next
    INDEX
    Explanations

    not listed or expressly

    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
     keine
    -0.08
     senza
    -0.07
     ไม่มี
    -0.07
     χωρίς
    -0.07
    ไม่มี
    -0.07
     ohne
    -0.06
    гідно
    -0.06
     कोणते
    -0.06
     zonder
    -0.06
     имеются
    -0.06
    POSITIVE LOGITS
     einfach
    0.07
     ఇప్పటికే
    0.06
     ব্যবস
    0.06
    但也
    0.06
     просто
    0.06
     pron
    0.06
     parameterized
    0.06
     cứ
    0.06
    avais
    0.06
     එය
    0.06
    Activations Density 0.011%

    No Known Activations