© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 129945
    Prev
    Next
    INDEX
    Explanations

    Posts, Set, Q prefixes

    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
     애플
    -0.06
    ječ
    -0.06
    下列
    -0.06
     前回
    -0.06
     %=
    -0.06
     高級
    -0.06
     henkil
    -0.06
     мә
    -0.06
    レベル
    -0.06
     Macri
    -0.06
    POSITIVE LOGITS
     are
    0.09
     from
    0.07
     for
    0.07
     dari
    0.06
     during
    0.06
     sont
    0.06
     to
    0.06
     do
    0.06
    recieve
    0.06
     of
    0.06
    Activations Density 0.001%

    No Known Activations