© 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. 119388
    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
     at
    -0.08
     aident
    -0.07
     the
    -0.07
     our
    -0.06
     on
    -0.06
     utilidad
    -0.06
    ኔ
    -0.06
     useful
    -0.06
     Util
    -0.06
    㕸
    -0.06
    POSITIVE LOGITS
     unremarkable
    0.06
     udah
    0.06
     unassuming
    0.06
    ),
    0.06
     shockingly
    0.06
    UEFA
    0.06
    致命
    0.06
     UEFA
    0.06
     거의
    0.05
     melod
    0.05
    Activations Density 0.000%

    No Known Activations