© 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. 117004
    Prev
    Next
    INDEX
    Explanations

    directory paths and include locations

    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
     indoor
    -0.06
     داخل
    -0.06
     outdoor
    -0.06
     স্থানীয়
    -0.05
     외부
    -0.05
     маленький
    -0.05
    るとき
    -0.05
     New
    -0.05
     নানা
    -0.05
     outside
    -0.05
    POSITIVE LOGITS
     najleps
    0.07
     数据
    0.06
     टूर्
    0.06
    }\
    0.06
     najbol
    0.06
     servicios
    0.06
     Saks
    0.06
     buku
    0.06
     satisf
    0.06
     Novi
    0.06
    Activations Density 0.004%

    No Known Activations