© 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. 128593
    Prev
    Next
    INDEX
    Explanations

    impact factor of

    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
     quién
    -0.07
     бетон
    -0.07
    asset
    -0.06
    Quién
    -0.06
     sightings
    -0.06
     энерго
    -0.05
     concert
    -0.05
    FUNCION
    -0.05
     गठबंधन
    -0.05
     fundraiser
    -0.05
    POSITIVE LOGITS
     evaluation
    0.08
     விட்டு
    0.07
     yearly
    0.07
     evaluates
    0.07
    評價
    0.07
     its
    0.06
     गिनती
    0.06
     constantly
    0.06
    評価
    0.06
    评价
    0.06
    Activations Density 0.004%

    No Known Activations