© 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. 129470
    Prev
    Next
    INDEX
    Explanations

    Internet carries

    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
     पि
    -0.06
     ১১
    -0.06
     গবেষণা
    -0.06
     серии
    -0.06
    ausea
    -0.06
    А
    -0.06
     ﷺ
    -0.06
     horror
    -0.06
    Я
    -0.06
    ザ
    -0.06
    POSITIVE LOGITS
     provides
    0.07
     creatively
    0.07
    )...
    0.07
     Influ
    0.07
     skillfully
    0.06
     directly
    0.06
     meticulous
    0.06
     boasts
    0.06
     boast
    0.06
     mainly
    0.06
    Activations Density 0.042%

    No Known Activations