© 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. 129030
    Prev
    Next
    INDEX
    Explanations

    GABA-stimulated responses

    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
     embody
    -0.06
     bilingual
    -0.06
    ီ
    -0.06
     Spiritual
    -0.06
    podob
    -0.06
     опыта
    -0.05
     麻
    -0.05
     sincerity
    -0.05
    abad
    -0.05
     تجربه
    -0.05
    POSITIVE LOGITS
     उत्पा
    0.08
     peningkatan
    0.06
    提高
    0.06
    อาจ
    0.06
     While
    0.06
     urządzenia
    0.06
     tăng
    0.06
     їх
    0.06
     their
    0.06
     alleine
    0.06
    Activations Density 0.080%

    No Known Activations