© 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. 129804
    Prev
    Next
    INDEX
    Explanations

    giving opinions or experiences

    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
    ที่จะ
    -0.07
     plethora
    -0.07
     and
    -0.07
    ທີ່ຈະ
    -0.07
     seçenek
    -0.07
     without
    -0.07
     our
    -0.07
     będzie
    -0.06
     vying
    -0.06
     글로벌
    -0.06
    POSITIVE LOGITS
     was
    0.08
     did
    0.07
     αυτή
    0.07
     этим
    0.07
    这是
    0.06
     had
    0.06
     இந்த
    0.06
    This
    0.06
    现在
    0.06
     этого
    0.06
    Activations Density 0.007%

    No Known Activations