© 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. 120615
    Prev
    Next
    INDEX
    Explanations

    defines contains implements

    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
     from
    -0.09
     diese
    -0.07
     từ
    -0.07
     από
    -0.07
     to
    -0.07
     fromi
    -0.06
     tidigare
    -0.06
     with
    -0.06
    จาก
    -0.06
    thisTrack
    -0.06
    POSITIVE LOGITS
     Google
    0.06
     just
    0.06
     text
    0.05
    ud
    0.05
    本日
    0.05
    bumptech
    0.05
    VI
    0.05
     gaping
    0.05
     kritik
    0.05
    rim
    0.05
    Activations Density 0.007%

    No Known Activations