© 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. 118592
    Prev
    Next
    INDEX
    Explanations

    "this" followed by code or punctuation

    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
     inertia
    -0.07
     ballistic
    -0.07
     because
    -0.06
     मजब
    -0.06
     momentum
    -0.06
     utc
    -0.06
     dynast
    -0.06
     righteous
    -0.06
    すべき
    -0.06
    Rewarded
    -0.06
    POSITIVE LOGITS
    ोजना
    0.06
    前記
    0.06
     cuidados
    0.06
     Snyder
    0.06
    出版
    0.06
     notice
    0.06
     tournaments
    0.06
    實際
    0.06
     participan
    0.06
     Somit
    0.06
    Activations Density 0.002%

    No Known Activations