© 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. 119884
    Prev
    Next
    INDEX
    Explanations

    news and informational articles

    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
     هذه
    -0.07
    㚼
    -0.06
    このような
    -0.06
    ——
    -0.06
     Goodyear
    -0.06
    another
    -0.06
     competitor
    -0.06
    यदि
    -0.06
    Mathematical
    -0.06
     by
    -0.06
    POSITIVE LOGITS
    まあ
    0.06
     infliction
    0.06
     मुताबिक
    0.06
     soar
    0.06
     desired
    0.06
    指的是
    0.06
    适用于
    0.06
     carefree
    0.06
     தனியார்
    0.06
     était
    0.06
    Activations Density 0.008%

    No Known Activations