© 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. 120096
    Prev
    Next
    INDEX
    Explanations

    schema, domain, namespace, scope

    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
    너무
    -0.06
     operatives
    -0.06
    ertas
    -0.06
     degenerate
    -0.06
    பிள்
    -0.06
    webserv
    -0.06
     incorrectly
    -0.06
    jari
    -0.06
     ஆப
    -0.06
     terrib
    -0.06
    POSITIVE LOGITS
     by
    0.06
    🇯
    0.06
     япон
    0.06
     официально
    0.06
     سطح
    0.06
     papan
    0.06
     jap
    0.06
     Официа
    0.06
     US
    0.06
     as
    0.05
    Activations Density 0.002%

    No Known Activations