© 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. 120380
    Prev
    Next
    INDEX
    Explanations

    useful marker surrogate objective

    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
     enorme
    -0.07
    普通的
    -0.07
     огром
    -0.07
     verschied
    -0.07
     보통
    -0.07
     огромное
    -0.07
     ogrom
    -0.06
     많은
    -0.06
     myriad
    -0.06
    多くの
    -0.06
    POSITIVE LOGITS
     कहें
    0.07
    workouts
    0.06
    Goals
    0.06
     potre
    0.06
     regulator
    0.06
    一致
    0.06
    比赛
    0.06
     necesidades
    0.06
     REGULATIONS
    0.06
     maintain
    0.06
    Activations Density 0.021%

    No Known Activations