© 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. 129221
    Prev
    Next
    INDEX
    Explanations

    font names

    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
    下の
    -0.06
    ಮೊ
    -0.06
    ﺨ
    -0.06
     sketchy
    -0.06
     افس
    -0.06
    の頃
    -0.06
    ilets
    -0.06
    ffine
    -0.06
    提高
    -0.06
     peculiarities
    -0.06
    POSITIVE LOGITS
     равномер
    0.06
    অনেক
    0.06
     நிச்சயமாக
    0.06
     वैरिएंट
    0.06
    Seems
    0.06
     surely
    0.06
    俨
    0.05
     \""
    0.05
    別途
    0.05
    miyor
    0.05
    Activations Density 0.001%

    No Known Activations