© 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. 129726
    Prev
    Next
    INDEX
    Explanations

    for

    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
     fief
    -0.06
    constitution
    -0.06
     introducir
    -0.06
     लोग
    -0.06
     vuelta
    -0.06
     různých
    -0.06
     Throughout
    -0.06
     TOR
    -0.06
     ट्रा
    -0.06
     لیے
    -0.05
    POSITIVE LOGITS
    Inspect
    0.06
    issimi
    0.06
     inspect
    0.06
     Fou
    0.06
    某
    0.05
     descending
    0.05
     சிங்க
    0.05
     enough
    0.05
     informiert
    0.05
     regret
    0.05
    Activations Density 0.015%

    No Known Activations