© 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. 119605
    Prev
    Next
    INDEX
    Explanations

    neither or both

    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
     entre
    -0.06
    /,
    -0.06
    ,
    -0.06
     사이에
    -0.06
    一起
    -0.06
    urs
    -0.05
    *,
    -0.05
    坐在
    -0.05
    課題
    -0.05
    、
    -0.05
    POSITIVE LOGITS
     khá
    0.08
     neither
    0.07
     vergleich
    0.07
     it
    0.07
     μεγαλύτε
    0.07
     velmi
    0.06
     lebih
    0.06
     bardzo
    0.06
    ithmetic
    0.06
     дуже
    0.06
    Activations Density 0.020%

    No Known Activations