© 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. 119658
    Prev
    Next
    INDEX
    Explanations

    package

    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
     okay
    -0.06
     নিশ্চয়
    -0.06
     Okay
    -0.06
     accessing
    -0.05
     déjà
    -0.05
     সম্ম
    -0.05
     with
    -0.05
     (?)
    -0.05
    Okay
    -0.05
     हिस्
    -0.05
    POSITIVE LOGITS
    它
    0.07
     ouvrage
    0.07
    避免
    0.07
    これにより
    0.07
     એક
    0.07
     говорить
    0.07
    Jumlah
    0.07
    使其
    0.07
    它的
    0.06
     તેને
    0.06
    Activations Density 0.002%

    No Known Activations