© 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. 128949
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
    oque
    -0.06
    ฯ
    -0.06
     即
    -0.05
    ก็
    -0.05
    hö
    -0.05
    kom
    -0.05
    爣
    -0.05
    ood
    -0.05
     tubing
    -0.05
     tabii
    -0.05
    POSITIVE LOGITS
     những
    0.08
     एक
    0.08
    이라는
    0.07
     andare
    0.07
    一個
    0.07
     but
    0.07
     такой
    0.07
     μια
    0.07
     один
    0.07
     предотвра
    0.07
    Activations Density 0.002%

    No Known Activations