© 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. 116724
    Prev
    Next
    INDEX
    Explanations

    Tranciscolabs, ATA Group, Edu-Execellence

    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
     modifica
    -0.07
     nedeniyle
    -0.07
     তাদের
    -0.06
    accessory
    -0.06
     ஜ
    -0.06
    被
    -0.06
     उनके
    -0.06
     Accessory
    -0.06
    DAYS
    -0.06
     सामाजिक
    -0.06
    POSITIVE LOGITS
     analogy
    0.06
     ხოლო
    0.05
    ümüz
    0.05
     midsole
    0.05
     Inspe
    0.05
     froid
    0.05
    jskiego
    0.05
     такую
    0.05
    lemme
    0.05
    }}+\
    0.05
    Activations Density 0.158%

    No Known Activations