© 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. 119400
    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
     چیک
    -0.06
    zzles
    -0.06
     аж
    -0.06
     slightly
    -0.06
    ℚ
    -0.06
     przez
    -0.06
    pointers
    -0.06
    (),
    -0.05
    Check
    -0.05
     Realty
    -0.05
    POSITIVE LOGITS
     lạ
    0.07
     senseless
    0.06
     scouting
    0.06
    萃
    0.06
     invitation
    0.06
     factory
    0.06
     invitación
    0.06
     অনুসন্ধান
    0.05
     sellest
    0.05
    elto
    0.05
    Activations Density 0.000%

    No Known Activations