© 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. 129241
    Prev
    Next
    INDEX
    Explanations

    coming on as substitute

    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
     intitul
    -0.07
     ensured
    -0.06
     SUMMER
    -0.06
    Summer
    -0.06
     μαζί
    -0.06
     Некоторые
    -0.06
     معه
    -0.06
     vissa
    -0.06
     APRIL
    -0.06
     возможно
    -0.06
    POSITIVE LOGITS
     by
    0.07
    utcnow
    0.06
     how
    0.06
     irritability
    0.06
     prossima
    0.06
     they
    0.06
     deploying
    0.06
    戦
    0.05
     próxima
    0.05
     readiness
    0.05
    Activations Density 0.008%

    No Known Activations