© 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. 129326
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation

    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
     неско
    -0.07
     any
    -0.07
    その他の
    -0.06
    Employ
    -0.06
     difficulty
    -0.06
     χρό
    -0.06
    जूद
    -0.06
     उल्लंघन
    -0.06
     other
    -0.06
     limitations
    -0.06
    POSITIVE LOGITS
     Without
    0.06
    如下
    0.06
     praised
    0.06
    Without
    0.06
     बुनियादी
    0.06
     four
    0.06
     Having
    0.06
     வெள்ளை
    0.05
     joined
    0.05
     toured
    0.05
    Activations Density 0.002%

    No Known Activations