© 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. 119529
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    vì
    -0.07
    とても
    -0.07
     vì
    -0.07
    next
    -0.06
     suelen
    -0.06
    すぐ
    -0.06
    very
    -0.06
    循
    -0.06
    Sehr
    -0.06
    すごく
    -0.06
    POSITIVE LOGITS
     sued
    0.06
    ****
    0.06
    ***********
    0.05
    ********
    0.05
    ⚖
    0.05
     dites
    0.05
    மைச்சர்
    0.05
     Required
    0.05
     capacitors
    0.05
     consist
    0.05
    Activations Density 0.011%

    No Known Activations