© 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. 128296
    Prev
    Next
    INDEX
    Explanations

    exposure and contaminants

    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
     назнача
    -0.06
     containing
    -0.06
     losers
    -0.05
    hore
    -0.05
     specifically
    -0.05
     stat
    -0.05
     ASSEMBLY
    -0.05
    错误
    -0.05
    ор
    -0.05
     배치
    -0.05
    POSITIVE LOGITS
     föränd
    0.07
     monthly
    0.07
     sebum
    0.07
     varía
    0.07
     suelen
    0.07
     autobi
    0.07
     fortn
    0.06
    candy
    0.06
    Get
    0.06
     તમારા
    0.06
    Activations Density 0.039%

    No Known Activations