© 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. 116483
    Prev
    Next
    INDEX
    Explanations

    MCD Application Team

    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
    보
    -0.06
     চু
    -0.06
    ಲ್ಲೂ
    -0.06
     স্বপ্নের
    -0.06
    God
    -0.06
     도전
    -0.06
    Iz
    -0.05
     કરવાનો
    -0.05
    comp
    -0.05
    যত
    -0.05
    POSITIVE LOGITS
     Despite
    0.08
     harmless
    0.06
     noirâtre
    0.06
    <h6>
    0.06
    依旧
    0.06
    Despite
    0.06
     người
    0.06
     comuns
    0.06
     anybody
    0.06
     znám
    0.06
    Activations Density 0.002%

    No Known Activations