© 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. 117014
    Prev
    Next
    INDEX
    Explanations

    money deducted or not received

    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
    大概
    -0.07
     emol
    -0.06
    得到
    -0.06
    用於
    -0.06
     alleine
    -0.06
    用于
    -0.06
    鷸
    -0.06
     KAHN
    -0.06
    zugs
    -0.06
     சூ
    -0.05
    POSITIVE LOGITS
     již
    0.06
    ভাষা
    0.06
     his
    0.06
     już
    0.06
     allerede
    0.06
     versatility
    0.06
     multif
    0.06
    multif
    0.06
     нова
    0.06
    郢
    0.06
    Activations Density 0.002%

    No Known Activations