© 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. 117999
    Prev
    Next
    INDEX
    Explanations

    code includes and headers

    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
     continually
    -0.07
     operate
    -0.07
     όταν
    -0.07
     continuously
    -0.07
     quando
    -0.06
     process
    -0.06
     constantly
    -0.06
     on
    -0.06
     or
    -0.06
     ständig
    -0.06
    POSITIVE LOGITS
    বাড়
    0.07
     southward
    0.06
    風景
    0.06
     *$
    0.06
    বাড়ি
    0.06
     northward
    0.06
     city
    0.06
    和
    0.06
     cityscape
    0.06
     gorges
    0.06
    Activations Density 0.003%

    No Known Activations