© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118485
    Prev
    Next
    INDEX
    Explanations

    quotation marks and numbers

    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
     কাপড়
    -0.06
     interdependence
    -0.06
     BEFORE
    -0.06
    www
    -0.06
    Zip
    -0.05
     hơn
    -0.05
     মহান
    -0.05
     código
    -0.05
     יותר
    -0.05
     تمت
    -0.05
    POSITIVE LOGITS
    引き続き
    0.07
    変わ
    0.06
     reste
    0.06
    억원
    0.06
     baada
    0.06
     Montréal
    0.06
    ళ్లు
    0.06
    Спољашње
    0.06
    ھا
    0.06
     weiterhin
    0.06
    Activations Density 0.001%

    No Known Activations