© 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. 116693
    Prev
    Next
    INDEX
    Explanations

    as to

    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
     להיות
    -0.07
     například
    -0.06
     contatto
    -0.06
    囪
    -0.06
     подума
    -0.06
     второго
    -0.06
     empezó
    -0.06
     connaissance
    -0.06
     ஒன்றாக
    -0.06
     знания
    -0.06
    POSITIVE LOGITS
     gestern
    0.06
    alingrad
    0.06
    ijos
    0.05
    ニング
    0.05
     nosotros
    0.05
    臊
    0.05
     Rovio
    0.05
    ecek
    0.05
    せ
    0.05
    রাম
    0.05
    Activations Density 0.007%

    No Known Activations