© 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. 128443
    Prev
    Next
    INDEX
    Explanations

    `Right now`

    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
    ție
    -0.06
     cavities
    -0.06
    chrift
    -0.06
     sejahtera
    -0.06
    ).
    -0.05
    things
    -0.05
     mientras
    -0.05
    <h5>
    -0.05
    》。
    -0.05
     noises
    -0.05
    POSITIVE LOGITS
     τον
    0.06
     malgré
    0.06
     وكذلك
    0.06
    (")
    0.06
     출발
    0.06
     zeal
    0.06
    Respect
    0.06
    无关
    0.06
    க்கொண்ட
    0.06
     renowned
    0.06
    Activations Density 0.001%

    No Known Activations