© 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. 119239
    Prev
    Next
    INDEX
    Explanations

    options and choices

    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
    特色的
    -0.07
     disagree
    -0.06
    Indirect
    -0.06
     generali
    -0.06
     estiver
    -0.06
    olli
    -0.06
     Teilnehmer
    -0.06
    indirect
    -0.06
     IRS
    -0.06
    ᡠ
    -0.06
    POSITIVE LOGITS
     options
    0.08
     opções
    0.07
    オプション
    0.07
     scalable
    0.07
     Optionen
    0.07
    options
    0.07
     option
    0.07
     offers
    0.07
     opção
    0.06
     adjustable
    0.06
    Activations Density 0.065%

    No Known Activations