© 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. 120652
    Prev
    Next
    INDEX
    Explanations

    further studies/Q: / new jersey

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     are
    -0.08
     adventures
    -0.07
     overly
    -0.06
    特征
    -0.06
     특징
    -0.06
    設備
    -0.06
     FISH
    -0.06
    を読む
    -0.06
     unusually
    -0.06
    VARCHAR
    -0.06
    POSITIVE LOGITS
     contributing
    0.07
     contribuir
    0.06
     contribute
    0.06
     girls
    0.06
     Nike
    0.06
     contribuer
    0.06
     contribu
    0.06
     लाता
    0.05
     項
    0.05
     Brands
    0.05
    Activations Density 0.003%

    No Known Activations