© 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. 117544
    Prev
    Next
    INDEX
    Explanations

    food ingredients

    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
     closer
    -0.06
     இல்லாமல்
    -0.06
     Balloons
    -0.06
     minorities
    -0.06
     вами
    -0.06
    autonomous
    -0.06
    enamefont
    -0.06
    养成
    -0.06
    គួរ
    -0.06
     cohesive
    -0.06
    POSITIVE LOGITS
    쟌
    0.06
    ヲ
    0.06
    考虑到
    0.06
     imediatamente
    0.06
    まだまだ
    0.06
     చర్య
    0.06
    las
    0.06
     mūsų
    0.06
     اپنے
    0.05
     ہمارے
    0.05
    Activations Density 0.008%

    No Known Activations