© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 131029
    Prev
    Next
    INDEX
    Explanations

    parentheses with single letters or 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
    When
    -0.11
     when
    -0.11
    when
    -0.09
     когда
    -0.08
     när
    -0.08
     cuando
    -0.07
     عندما
    -0.07
    Cuando
    -0.07
     زمانی
    -0.07
    Когда
    -0.07
    POSITIVE LOGITS
    :
    0.09
    ;
    0.07
    =
    0.07
     has
    0.06
     average
    0.06
     Z
    0.06
     grossly
    0.06
     nearly
    0.05
     extremely
    0.05
    :"
    0.05
    Activations Density 0.010%

    No Known Activations