© 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. 129191
    Prev
    Next
    INDEX
    Explanations

    URLs, paths, and numbers

    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
     If
    -0.07
     next
    -0.06
     brought
    -0.06
    ("",
    -0.06
     affords
    -0.06
     However
    -0.06
     catapult
    -0.05
     sljede
    -0.05
     இன்று
    -0.05
     dữ
    -0.05
    POSITIVE LOGITS
    用
    0.08
     آنچه
    0.07
     باستخدام
    0.07
     समस्याएं
    0.06
    有用
    0.06
    。
    0.06
     alkalmaz
    0.06
     akkor
    0.06
    使用
    0.06
     použití
    0.06
    Activations Density 0.005%

    No Known Activations