© 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. 119604
    Prev
    Next
    INDEX
    Explanations

    `#![allow`

    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
                  
    -0.06
     yani
    -0.06
    包括
    -0.06
     той
    -0.06
     यानी
    -0.06
    querySelector
    -0.06
     दिखाता
    -0.06
     अर्थात
    -0.06
     অর্থাৎ
    -0.06
     those
    -0.06
    POSITIVE LOGITS
     apesar
    0.06
     Usted
    0.06
     penatibus
    0.06
     ascribed
    0.06
    以上の
    0.06
     parametros
    0.06
     sincer
    0.06
     ultimately
    0.06
    вто
    0.05
     tasarım
    0.05
    Activations Density 0.002%

    No Known Activations