© 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. 117984
    Prev
    Next
    INDEX
    Explanations

    on Windows

    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
     страны
    -0.06
    ってくる
    -0.06
     нужно
    -0.06
     Citt
    -0.06
     не
    -0.06
     потрібно
    -0.06
     at
    -0.06
    ഘാ
    -0.06
     trzeba
    -0.06
    海の
    -0.06
    POSITIVE LOGITS
    成為
    0.07
     makes
    0.07
     membuat
    0.06
     making
    0.06
    成为
    0.06
     يجعل
    0.06
     make
    0.06
     باعث
    0.06
    讓
    0.06
    itious
    0.06
    Activations Density 0.058%

    No Known Activations