© 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. 128617
    Prev
    Next
    INDEX
    Explanations

    names and professions

    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
     our
    -0.07
     possible
    -0.07
     changeable
    -0.07
    主な
    -0.06
     those
    -0.06
     these
    -0.06
     inferences
    -0.06
     one
    -0.06
     this
    -0.06
     gets
    -0.06
    POSITIVE LOGITS
     ayudará
    0.07
    Ive
    0.06
    如果
    0.06
    不需要
    0.06
     cidad
    0.05
     pathlib
    0.05
    同样
    0.05
     Wirkung
    0.05
    が含ま
    0.05
     permitirá
    0.05
    Activations Density 0.001%

    No Known Activations