© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130683
    Prev
    Next
    INDEX
    Explanations

    there is / has been / taken over

    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
    шается
    -0.06
     مشینوں
    -0.06
     Ayam
    -0.06
     则
    -0.06
    itical
    -0.06
     మరో
    -0.06
    لس
    -0.06
     பிரச்
    -0.06
    ことに
    -0.06
     наве
    -0.06
    POSITIVE LOGITS
     הם
    0.06
     sect
    0.06
    及
    0.06
     현재
    0.06
    현재
    0.05
     terbesar
    0.05
     largest
    0.05
    Envelope
    0.05
     टोटल
    0.05
     deine
    0.05
    Activations Density 0.006%

    No Known Activations