© 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. 130105
    Prev
    Next
    INDEX
    Explanations

    relatively [adjective]

    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
     
    -0.07
    ↵
    -0.07
     going
    -0.06
     GAAP
    -0.06
     довольно
    -0.06
     recovering
    -0.06
    很
    -0.06
    apt
    -0.06
     सुमारे
    -0.06
    sup
    -0.06
    POSITIVE LOGITS
     continúa
    0.07
     ángulo
    0.07
    Regardless
    0.07
     любы
    0.07
    лює
    0.07
     Regardless
    0.07
     અન્ય
    0.07
     utilisent
    0.07
     acolo
    0.07
     любом
    0.06
    Activations Density 0.008%

    No Known Activations