© 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. 116374
    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
     삼
    -0.06
     matin
    -0.06
    ED
    -0.05
    काळी
    -0.05
     :
    -0.05
     الثلاث
    -0.05
     when
    -0.05
     on
    -0.05
     drie
    -0.05
     tři
    -0.05
    POSITIVE LOGITS
    请求
    0.08
    🎱
    0.07
    except
    0.07
    🧸
    0.07
    🐲
    0.07
    Suggestion
    0.07
     requests
    0.07
     suggests
    0.07
    🤬
    0.07
     とする
    0.06
    Activations Density 0.000%

    No Known Activations