© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 119952
    Prev
    Next
    INDEX
    Explanations

    Escherichia coli

    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
     another
    -0.07
     actualmente
    -0.07
     شركة
    -0.07
     also
    -0.07
    ளிலும்
    -0.07
     otro
    -0.06
     también
    -0.06
     också
    -0.06
     negra
    -0.06
    另一个
    -0.05
    POSITIVE LOGITS
     পাবার
    0.06
     භාවිතා
    0.06
     excès
    0.06
     പ്രവര്‍
    0.06
     بنابراین
    0.06
    items
    0.06
     سننے
    0.06
     Magdalena
    0.06
     pronunci
    0.06
     વસ્તુ
    0.06
    Activations Density 0.007%

    No Known Activations