© 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. 116604
    Prev
    Next
    INDEX
    Explanations

    case numbers

    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
    middle
    -0.06
     it
    -0.06
     الله
    -0.06
    data
    -0.06
    Middle
    -0.05
     estos
    -0.05
     cấu
    -0.05
     एसडीएम
    -0.05
     to
    -0.05
     in
    -0.05
    POSITIVE LOGITS
    例えば
    0.06
     wives
    0.06
    认为
    0.06
     فترة
    0.06
     powin
    0.06
     If
    0.06
     பெரிய
    0.06
     conundrum
    0.06
    WATCH
    0.06
    🧜
    0.06
    Activations Density 0.001%

    No Known Activations