© 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. 119340
    Prev
    Next
    INDEX
    Explanations

    family history research and genealogy

    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
    STRONG
    -0.06
    量は
    -0.06
     volgen
    -0.06
     habitudes
    -0.06
     रेन
    -0.06
    만의
    -0.06
     masih
    -0.06
     ಹೆಸರು
    -0.05
    మన్
    -0.05
     różne
    -0.05
    POSITIVE LOGITS
    asian
    0.06
    intended
    0.06
     fest
    0.06
     विधेयक
    0.06
    बता
    0.05
    らかじめ
    0.05
    stop
    0.05
    𝐣
    0.05
     offending
    0.05
    ended
    0.05
    Activations Density 0.005%

    No Known Activations