© 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. 117119
    Prev
    Next
    INDEX
    Explanations

    scientific entities following 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
    頑張
    -0.06
    その後
    -0.06
     threes
    -0.06
     thence
    -0.06
     each
    -0.06
     prototyping
    -0.06
    ૩
    -0.06
     abruptly
    -0.06
     쭉
    -0.06
    problems
    -0.06
    POSITIVE LOGITS
     would
    0.08
     двумя
    0.06
     न्यायालय
    0.06
     部分
    0.06
     acuerdo
    0.06
     teilweise
    0.06
    Would
    0.05
     could
    0.05
     >,
    0.05
    issen
    0.05
    Activations Density 0.006%

    No Known Activations