© 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. 130436
    Prev
    Next
    INDEX
    Explanations

    text starting with Q: or Other

    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
     with
    -0.09
     শুধুমাত্র
    -0.08
     WITH
    -0.08
     With
    -0.07
     بال
    -0.07
     dengan
    -0.07
     با
    -0.07
     Dengan
    -0.06
    著名
    -0.06
     avec
    -0.06
    POSITIVE LOGITS
    yaml
    0.06
    ৪০
    0.06
     vikt
    0.06
     llegado
    0.06
    直播
    0.06
     ocho
    0.05
     coordinate
    0.05
     minutos
    0.05
    Mi
    0.05
    debug
    0.05
    Activations Density 0.003%

    No Known Activations