© 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. 120399
    Prev
    Next
    INDEX
    Explanations

    unpublished disposition

    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
     decidedly
    -0.07
     warmly
    -0.06
     establishes
    -0.06
     solemnly
    -0.06
     подробно
    -0.06
     germs
    -0.06
     delightfully
    -0.06
     allowing
    -0.06
     deviations
    -0.06
     maraming
    -0.06
    POSITIVE LOGITS
     alguna
    0.06
    Some
    0.06
     Somehow
    0.06
     pratica
    0.06
    인데
    0.06
    ज्ञ
    0.06
    部分的
    0.06
     Ngo
    0.06
    ிகை
    0.05
     கரை
    0.05
    Activations Density 0.001%

    No Known Activations