© 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. 116976
    Prev
    Next
    INDEX
    Explanations

    `border-radius`, `border-bottom`, `border-0`

    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
     मर्ज
    -0.05
    चाल
    -0.05
    ியது
    -0.05
     स्ट्रीम
    -0.05
    দেহ
    -0.05
     pozorn
    -0.05
     서로
    -0.05
     penuh
    -0.05
     cient
    -0.05
     বেশি
    -0.05
    POSITIVE LOGITS
     sehingga
    0.07
    으로서
    0.07
     Lill
    0.07
     digitization
    0.07
     Illustrator
    0.07
     below
    0.07
    preprocessing
    0.06
    垕
    0.06
     sekaligus
    0.06
    所以在
    0.06
    Activations Density 0.005%

    No Known Activations