© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118459
    Prev
    Next
    INDEX
    Explanations

    alphanumeric sequences and identifiers

    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
     the
    -0.06
     계속
    -0.06
     climber
    -0.06
     гля
    -0.06
    बाह
    -0.06
     ආර
    -0.06
    Panel
    -0.06
     дальней
    -0.06
    If
    -0.06
    因此
    -0.06
    POSITIVE LOGITS
     современных
    0.07
     exquisitely
    0.07
     mesmo
    0.07
     same
    0.06
     même
    0.06
     삽니다
    0.06
    ములు
    0.06
     خمس
    0.06
    fourth
    0.06
     उपयोगी
    0.06
    Activations Density 0.002%

    No Known Activations