© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118025
    Prev
    Next
    INDEX
    Explanations

    fungi, mushrooms, biological terms

    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
    ✈
    -0.06
     prevailed
    -0.06
     написать
    -0.06
     airway
    -0.06
     सफलतापूर्वक
    -0.06
     individu
    -0.06
     prevail
    -0.06
     Individuals
    -0.06
    convolve
    -0.06
     défendre
    -0.06
    POSITIVE LOGITS
     informativo
    0.07
     дослід
    0.06
     gesprek
    0.06
     reset
    0.06
     électrique
    0.06
     UBND
    0.06
     애플
    0.06
     Experten
    0.06
     informative
    0.06
     بازار
    0.06
    Activations Density 0.010%

    No Known Activations