© 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. 116756
    Prev
    Next
    INDEX
    Explanations

    creation date or timestamp

    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
     могло
    -0.07
     now
    -0.07
     ServiceNow
    -0.06
     jetzt
    -0.06
     pudo
    -0.06
     comprehensive
    -0.06
    最新
    -0.06
     puede
    -0.06
    かなり
    -0.06
     poiché
    -0.06
    POSITIVE LOGITS
     استفاده
    0.07
    使用
    0.06
     использова
    0.06
     intersections
    0.06
    utral
    0.06
     Banker
    0.06
    Ე
    0.05
    unakan
    0.05
    ევე
    0.05
     pasti
    0.05
    Activations Density 0.001%

    No Known Activations