© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120731
    Prev
    Next
    INDEX
    Explanations

    Q: Introduction

    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
     também
    -0.08
     також
    -0.07
     gunakan
    -0.07
    なども
    -0.07
     también
    -0.07
     ٻ
    -0.06
    RestorePolicy
    -0.06
    ేవ
    -0.06
     sebagai
    -0.06
     sarà
    -0.06
    POSITIVE LOGITS
     never
    0.07
    never
    0.07
    No
    0.06
     supposedly
    0.06
     सरिया
    0.06
    Never
    0.06
    多数
    0.06
     purportedly
    0.05
    WHERE
    0.05
    umpy
    0.05
    Activations Density 0.001%

    No Known Activations