© 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. 129631
    Prev
    Next
    INDEX
    Explanations

    essential nutrients and factors

    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
    alker
    -0.07
     einzelnen
    -0.06
     makes
    -0.06
     talked
    -0.06
     hizo
    -0.06
    داف
    -0.06
     Chaucer
    -0.06
     AIDS
    -0.06
     Shakespeare
    -0.06
     например
    -0.06
    POSITIVE LOGITS
     प्रोटो
    0.06
     worst
    0.06
     TSN
    0.06
     سبک
    0.06
     термо
    0.06
     Consid
    0.06
    gna
    0.06
     ऑगस्ट
    0.05
     Worse
    0.05
    Mechanical
    0.05
    Activations Density 0.005%

    No Known Activations