© 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. 116782
    Prev
    Next
    INDEX
    Explanations

    Citations or references

    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
     leisure
    -0.07
     Tajik
    -0.07
    ضح
    -0.07
     हमेशा
    -0.07
     mengatakan
    -0.07
    unexpected
    -0.06
     తీసుకోవ
    -0.06
    relax
    -0.06
     મને
    -0.06
     이야기를
    -0.06
    POSITIVE LOGITS
     with
    0.07
     who
    0.06
     शिवाय
    0.06
     at
    0.06
     With
    0.06
     as
    0.06
    近年
    0.05
     частина
    0.05
    会被
    0.05
     für
    0.05
    Activations Density 0.007%

    No Known Activations