© 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. 117403
    Prev
    Next
    INDEX
    Explanations

    config, error, communication

    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
    があった
    -0.06
     advertised
    -0.06
     ep
    -0.06
     CLAIM
    -0.06
     claim
    -0.05
    始まった
    -0.05
    ist
    -0.05
     [
    -0.05
    gehen
    -0.05
     conosci
    -0.05
    POSITIVE LOGITS
     전체
    0.07
     necessariamente
    0.07
     이러한
    0.07
     necesariamente
    0.07
     необходи
    0.07
     필요한
    0.07
     frågor
    0.07
    出席
    0.07
     keseluruhan
    0.07
    必需
    0.07
    Activations Density 0.001%

    No Known Activations