© 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. 128661
    Prev
    Next
    INDEX
    Explanations

    agreement and collaboration

    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
     diseñar
    -0.07
     improvement
    -0.07
    可怕
    -0.06
     Improvement
    -0.06
     ropa
    -0.06
    铤
    -0.06
     crude
    -0.06
    trying
    -0.06
     protection
    -0.06
     otra
    -0.06
    POSITIVE LOGITS
     fandom
    0.07
     eagerly
    0.07
     gladly
    0.07
     deliciously
    0.07
     بسیار
    0.06
     soulful
    0.06
     गोष्टी
    0.06
     firmly
    0.06
     beautifully
    0.06
     перегово
    0.06
    Activations Density 0.003%

    No Known Activations