© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 130573
    Prev
    Next
    INDEX
    Explanations

    names ending in y or e

    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
     monitor
    -0.06
    っています
    -0.06
     shrinking
    -0.06
     màu
    -0.05
    ったり
    -0.05
    Red
    -0.05
     путем
    -0.05
     મહે
    -0.05
    tsc
    -0.05
     വെ
    -0.05
    POSITIVE LOGITS
    百万
    0.06
     प्रतिष्ठा
    0.06
     forbidden
    0.06
     вопроса
    0.06
     proib
    0.06
    budget
    0.06
     рейтинг
    0.06
     Quan
    0.06
     determines
    0.06
     отправить
    0.06
    Activations Density 0.011%

    No Known Activations