© 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. 128317
    Prev
    Next
    INDEX
    Explanations

    k

    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
     content
    -0.06
     moderated
    -0.06
    М
    -0.05
     சொந்த
    -0.05
    堛
    -0.05
    ဆင့်
    -0.05
     hosp
    -0.05
    amed
    -0.05
     gewähr
    -0.05
    ında
    -0.05
    POSITIVE LOGITS
     теории
    0.06
     আপাতত
    0.06
    ribute
    0.06
     theories
    0.06
     vooral
    0.06
     basically
    0.06
     Highest
    0.06
    FOOT
    0.06
    ムー
    0.06
    igste
    0.06
    Activations Density 0.001%

    No Known Activations