© 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. 116232
    Prev
    Next
    INDEX
    Explanations

    Project summary, Margaret Hoover

    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
    fuss
    -0.06
     Windows
    -0.06
     when
    -0.05
     এটির
    -0.05
    ंकज
    -0.05
     toward
    -0.05
    midt
    -0.05
    ↵
    -0.05
     Kt
    -0.05
     without
    -0.05
    POSITIVE LOGITS
     termasuk
    0.07
    を行い
    0.07
    成為
    0.07
     كله
    0.06
    旃
    0.06
    来看看
    0.06
     world
    0.06
     पोहो
    0.06
     někter
    0.06
    ური
    0.06
    Activations Density 0.001%

    No Known Activations