© 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. 129989
    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
     discarding
    -0.06
     ご
    -0.06
     с
    -0.06
     Anfield
    -0.06
     አይ
    -0.06
     ignore
    -0.06
     お
    -0.06
     Ignore
    -0.06
    bu
    -0.05
    alis
    -0.05
    POSITIVE LOGITS
     piuttosto
    0.08
     sehr
    0.07
     необы
    0.06
    峭
    0.06
     eder
    0.06
     DETERMIN
    0.06
    सिला
    0.06
     malade
    0.06
     lejos
    0.06
    بد
    0.06
    Activations Density 0.000%

    No Known Activations