© 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. 119342
    Prev
    Next
    INDEX
    Explanations

    examples of Hanukkah, instances, birds, or survivors

    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
    ujący
    -0.07
             
    -0.06
     এক
    -0.06
    どのような
    -0.06
     in
    -0.06
     অল্প
    -0.06
    ...
    -0.06
     एक
    -0.06
    ным
    -0.06
     um
    -0.05
    POSITIVE LOGITS
     აქვს
    0.06
     メ
    0.06
     демонстри
    0.06
     остальные
    0.06
     troughs
    0.06
     makes
    0.06
    reason
    0.06
    時間が
    0.06
     laki
    0.06
     demonstrates
    0.06
    Activations Density 0.001%

    No Known Activations