© 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. 116878
    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
     adequately
    -0.07
     sufficiently
    -0.06
     proficient
    -0.06
     subsequently
    -0.06
     reliable
    -0.06
     sufficient
    -0.06
     adequate
    -0.06
     competent
    -0.05
    ရောက်
    -0.05
     fairly
    -0.05
    POSITIVE LOGITS
     сказал
    0.07
    尕
    0.07
     reckoning
    0.06
    🍻
    0.06
    这些
    0.06
     umožňuje
    0.06
     लिखा
    0.06
     all
    0.06
     history
    0.06
    种种
    0.06
    Activations Density 0.003%

    No Known Activations