© 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. 120163
    Prev
    Next
    INDEX
    Explanations

    boss fights or gym battles

    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
    deployed
    -0.06
     ܡ
    -0.06
     από
    -0.06
     뒤
    -0.06
    物资
    -0.05
     roughly
    -0.05
     deployed
    -0.05
    కాలు
    -0.05
     costante
    -0.05
     অমৃত
    -0.05
    POSITIVE LOGITS
     يع
    0.07
     учителя
    0.06
     reasoning
    0.06
     நுரையீரல்
    0.06
     సంగీ
    0.06
    Requires
    0.06
     conclus
    0.06
     pessoa
    0.06
     concluding
    0.06
    推理
    0.06
    Activations Density 0.006%

    No Known Activations