© 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. 128763
    Prev
    Next
    INDEX
    Explanations

    new or additional

    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
     work
    -0.08
    umably
    -0.06
     behaves
    -0.06
     பணி
    -0.06
    Согласно
    -0.06
    work
    -0.06
    <strong>
    -0.06
     possess
    -0.06
    很多人
    -0.06
     care
    -0.05
    POSITIVE LOGITS
     新款
    0.08
     новых
    0.07
     त्यस
    0.07
     neuen
    0.07
    を追加
    0.07
     nuovi
    0.07
     추가
    0.07
    新たな
    0.07
     nieuwe
    0.07
     nuevos
    0.07
    Activations Density 0.004%

    No Known Activations