© 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. 117072
    Prev
    Next
    INDEX
    Explanations

    ATLAS excludes

    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
     attendee
    -0.07
     jedem
    -0.07
     każdego
    -0.06
    每一个
    -0.06
     каждого
    -0.06
    每一個
    -0.06
     customized
    -0.06
     mehrere
    -0.06
     każdy
    -0.06
     neues
    -0.06
    POSITIVE LOGITS
     forecasts
    0.06
    河北
    0.05
     date
    0.05
     vile
    0.05
    τική
    0.05
     facto
    0.05
    method
    0.05
    뜨
    0.05
    щее
    0.05
     naf
    0.05
    Activations Density 0.003%

    No Known Activations