© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116992
    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
     on
    -0.07
     sh
    -0.07
     कोणत्याही
    -0.07
    öner
    -0.06
     Dh
    -0.06
     qualquer
    -0.06
    steering
    -0.06
     Hope
    -0.06
     Grilled
    -0.06
     Any
    -0.06
    POSITIVE LOGITS
     véritable
    0.06
    вра
    0.06
    真正
    0.06
     each
    0.06
     vraie
    0.06
     truly
    0.05
     তহবিল
    0.05
    认真
    0.05
     Picard
    0.05
     verdadero
    0.05
    Activations Density 0.000%

    No Known Activations