© 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. 128708
    Prev
    Next
    INDEX
    Explanations

    legislator, dan, career, headed

    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
     anticipated
    -0.07
    vorm
    -0.06
    anticipated
    -0.06
     inflamed
    -0.06
     kanssa
    -0.06
     interplay
    -0.06
     matchups
    -0.06
     perceived
    -0.06
    交互
    -0.06
    idores
    -0.06
    POSITIVE LOGITS
     popular
    0.06
    Investigators
    0.06
    popular
    0.06
     식이
    0.06
    Prefer
    0.06
     wissenschaft
    0.06
     provavelmente
    0.05
    ダン
    0.05
    дан
    0.05
     investigative
    0.05
    Activations Density 0.057%

    No Known Activations