© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119182
    Prev
    Next
    INDEX
    Explanations

    title followed by colon or quote

    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
     confidence
    -0.06
    ريف
    -0.06
     structurally
    -0.06
    ރ
    -0.06
     intervals
    -0.06
    intervals
    -0.06
    rias
    -0.06
     చేసింది
    -0.06
     cette
    -0.06
     originality
    -0.05
    POSITIVE LOGITS
     कैसा
    0.07
     선수
    0.07
     weiteren
    0.07
     opção
    0.06
     получить
    0.06
     기자
    0.06
    spunkt
    0.06
     that
    0.06
     причина
    0.06
     (!)
    0.06
    Activations Density 0.002%

    No Known Activations