© 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. 119622
    Prev
    Next
    INDEX
    Explanations

    come together

    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
    ก็
    -0.08
    អ្វី
    -0.07
     also
    -0.07
     basically
    -0.07
     také
    -0.07
     arī
    -0.07
     أيضًا
    -0.07
     أيضا
    -0.07
     juga
    -0.06
     också
    -0.06
    POSITIVE LOGITS
     அவற்றை
    0.06
    พระ
    0.06
     interactions
    0.06
    说到
    0.06
     असल्याचे
    0.06
     عند
    0.06
    請
    0.06
    -
    0.06
    安全
    0.06
     affer
    0.06
    Activations Density 0.066%

    No Known Activations