© 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. 119973
    Prev
    Next
    INDEX
    Explanations

    official documents and revisions

    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
     سواء
    -0.06
     Sports
    -0.06
     ಕೂಡ
    -0.06
     idem
    -0.06
     discriminatory
    -0.05
     promised
    -0.05
    Asian
    -0.05
     mismo
    -0.05
     fingers
    -0.05
     accordingly
    -0.05
    POSITIVE LOGITS
     наш
    0.07
     அழகான
    0.06
     vårt
    0.06
    蛉
    0.06
     которое
    0.06
     Possibly
    0.06
     nosso
    0.06
     expend
    0.06
     изго
    0.06
    ([\
    0.06
    Activations Density 0.001%

    No Known Activations