© 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. 116786
    Prev
    Next
    INDEX
    Explanations

    analysis, analytics, mining

    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
    Chairman
    -0.07
     schwarzen
    -0.06
    ලි
    -0.06
    chairman
    -0.06
    正常的
    -0.06
     bruke
    -0.06
     Chairman
    -0.06
    ViewHolder
    -0.06
    landı
    -0.06
     manejo
    -0.06
    POSITIVE LOGITS
    大多
    0.07
    目前
    0.07
     ubicado
    0.07
    位于
    0.06
     目前
    0.06
    னிய
    0.06
     yes
    0.06
     dimly
    0.06
    currently
    0.06
    єднання
    0.06
    Activations Density 0.008%

    No Known Activations