© 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. 118276
    Prev
    Next
    INDEX
    Explanations

    code delimiters or multiline structures

    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
     which
    -0.07
    וה
    -0.06
     ably
    -0.06
    Item
    -0.06
    ++++++++++++++++
    -0.06
    .,
    -0.05
     abundantly
    -0.05
     continuing
    -0.05
    டுகள்
    -0.05
     والذي
    -0.05
    POSITIVE LOGITS
     по
    0.07
     también
    0.07
    本身
    0.07
     никогда
    0.07
    其实
    0.07
    เตอร์
    0.07
    कायदा
    0.06
     eigenlijk
    0.06
     própria
    0.06
     vendidos
    0.06
    Activations Density 0.001%

    No Known Activations