© 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. 129448
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation or operators

    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
    upi
    -0.06
    editar
    -0.06
    ostructures
    -0.06
    หรือ
    -0.06
     or
    -0.06
     स्टार्ट
    -0.05
    IsValid
    -0.05
    }}
    -0.05
     اصلاح
    -0.05
     tarifas
    -0.05
    POSITIVE LOGITS
     here
    0.07
     எந்த
    0.07
    任何
    0.07
     Rott
    0.07
     any
    0.07
    যখন
    0.07
     đây
    0.06
     Primavera
    0.06
     schle
    0.06
     whenever
    0.06
    Activations Density 0.001%

    No Known Activations