© 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. 116363
    Prev
    Next
    INDEX
    Explanations

    forwarded emails

    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
     आफ्टर
    -0.07
     worms
    -0.06
     multitude
    -0.06
     través
    -0.06
    MathML
    -0.06
     motores
    -0.05
     perc
    -0.05
    ből
    -0.05
    率为
    -0.05
    不是
    -0.05
    POSITIVE LOGITS
     экскур
    0.08
     காரணம்
    0.06
    軽減
    0.06
     ちゃっ
    0.06
     גם
    0.06
     ajud
    0.06
     karena
    0.06
     insensitive
    0.06
     пришлось
    0.06
     অভিহিত
    0.06
    Activations Density 0.003%

    No Known Activations