© 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. 130484
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     astăzi
    -0.06
     उतनी
    -0.06
    によっては
    -0.06
     मम
    -0.06
    লায়
    -0.06
     restauración
    -0.06
     ചില
    -0.06
    soluble
    -0.06
     dirección
    -0.06
     debate
    -0.06
    POSITIVE LOGITS
     constitutive
    0.06
    $(
    0.06
     which
    0.06
     pp
    0.06
     constit
    0.06
    ซึ่ง
    0.06
    rectangle
    0.06
    仍在
    0.05
     परमाण
    0.05
     transforma
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.