© 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. 128951
    Prev
    Next
    INDEX
    Explanations

    directions and routes

    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
     сило
    -0.06
     seguir
    -0.06
     away
    -0.06
     Shr
    -0.05
     sien
    -0.05
    ▃
    -0.05
     францу
    -0.05
    timeLeft
    -0.05
    iest
    -0.05
    牵
    -0.05
    POSITIVE LOGITS
     mãe
    0.07
     では
    0.06
     엄마
    0.06
    either
    0.06
     அதிக
    0.06
     structure
    0.06
    mıştır
    0.06
     acesta
    0.06
     späteren
    0.06
    消化
    0.06
    Activations Density 0.004%

    No Known Activations