© 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. 119189
    Prev
    Next
    INDEX
    Explanations

    foolishness or lack of intelligence

    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
    -0.07
     what
    -0.07
     cuando
    -0.07
    when
    -0.06
     quando
    -0.06
     nessuna
    -0.06
    hofer
    -0.05
    When
    -0.05
     Jaff
    -0.05
    what
    -0.05
    POSITIVE LOGITS
     stupidity
    0.07
     глу
    0.07
     silly
    0.07
     ridiculous
    0.06
     by
    0.06
     in
    0.06
     insanity
    0.06
     レディース
    0.06
     nonsense
    0.06
     particularly
    0.06
    Activations Density 0.010%

    No Known Activations