© 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. 129749
    Prev
    Next
    INDEX
    Explanations

    Montell, After Monkey, Maintain Application, Q:

    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
     questo
    -0.08
     so
    -0.07
     just
    -0.07
     tämän
    -0.06
     at
    -0.06
     meestal
    -0.06
     in
    -0.06
     because
    -0.06
    的這個
    -0.06
     as
    -0.06
    POSITIVE LOGITS
     permita
    0.06
     permite
    0.06
     música
    0.06
    믈
    0.06
     необхід
    0.06
     отсутствует
    0.06
     পারস্প
    0.06
    onics
    0.06
     необходимо
    0.06
     erfolgt
    0.06
    Activations Density 0.002%

    No Known Activations