© 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. 117159
    Prev
    Next
    INDEX
    Explanations

    events followed by descriptions

    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
     then
    -0.07
     such
    -0.07
     বেশকিছু
    -0.06
     unspecified
    -0.06
    groups
    -0.06
     سپس
    -0.06
    along
    -0.06
     along
    -0.05
     inoltre
    -0.05
     idempot
    -0.05
    POSITIVE LOGITS
     durch
    0.07
     가족
    0.07
     wirklich
    0.07
     wanneer
    0.07
     вас
    0.06
     oleh
    0.06
     về
    0.06
     veramente
    0.06
     Oggi
    0.06
     naprawdę
    0.06
    Activations Density 0.006%

    No Known Activations