© 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. 116952
    Prev
    Next
    INDEX
    Explanations

    error handling and logging

    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
     показывает
    -0.06
     बाय
    -0.06
     faster
    -0.06
    dont
    -0.06
     अल्कोहल
    -0.06
     suele
    -0.06
     accelerates
    -0.05
    on
    -0.05
    fe
    -0.05
     reconocimiento
    -0.05
    POSITIVE LOGITS
     ailing
    0.07
     übernommen
    0.06
    gcj
    0.06
     inaccuracy
    0.06
    ∴
    0.06
     they
    0.06
    何度も
    0.06
     elated
    0.06
     divs
    0.06
     בצ
    0.06
    Activations Density 0.002%

    No Known Activations