© 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. 116437
    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
     bring
    -0.05
    ato
    -0.05
     an
    -0.05
     other
    -0.05
     -
    -0.05
     mechanistic
    -0.05
    ใช้ง
    -0.05
     Rude
    -0.05
     streaming
    -0.05
     সংঘ
    -0.05
    POSITIVE LOGITS
     restrictions
    0.09
     restriction
    0.09
     prohibiting
    0.09
     restricting
    0.09
     restrict
    0.08
    restrict
    0.08
     restrictive
    0.08
     Restriction
    0.08
     restric
    0.07
    限制
    0.07
    Activations Density 0.000%

    No Known Activations