© 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. 117672
    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
     Quebec
    -0.06
     appropriate
    -0.06
     libraries
    -0.06
     gestionar
    -0.06
    Employees
    -0.06
     moieties
    -0.06
    achievement
    -0.06
     Zeitung
    -0.06
     ACHIEVEMENT
    -0.06
     Achievement
    -0.06
    POSITIVE LOGITS
    غیر
    0.06
     cannot
    0.06
    力
    0.06
     نہیں
    0.05
    ijt
    0.05
     hundreds
    0.05
     hijo
    0.05
     reaffirmed
    0.05
     बर्थ
    0.05
     Cannot
    0.05
    Activations Density 0.000%

    No Known Activations