© 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. 129114
    Prev
    Next
    INDEX
    Explanations

    A:

    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
     efectos
    -0.07
     जर्म
    -0.06
     func
    -0.06
    ходил
    -0.06
    IMF
    -0.06
     dört
    -0.06
     మాత్రం
    -0.06
     슈
    -0.06
     сочета
    -0.06
     совокуп
    -0.06
    POSITIVE LOGITS
     অনুরোধ
    0.07
     samego
    0.06
     മാത്രമേ
    0.06
     planification
    0.06
     যাবার
    0.06
    лери
    0.05
     OPTIONS
    0.05
     बध
    0.05
    Subscriptions
    0.05
    बहुत
    0.05
    Activations Density 0.019%

    No Known Activations