© 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. 129062
    Prev
    Next
    INDEX
    Explanations

    position, slower, forwards, temperature

    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
     what
    -0.07
     همین
    -0.07
    !!
    -0.07
     كانت
    -0.06
    什么
    -0.06
     前
    -0.06
     새로운
    -0.06
    是什么
    -0.06
     同じ
    -0.06
     neue
    -0.06
    POSITIVE LOGITS
     from
    0.07
     एकूण
    0.06
     однако
    0.06
     destinée
    0.06
    asi
    0.06
     toutefois
    0.06
     born
    0.06
    तो
    0.06
     Born
    0.06
     in
    0.05
    Activations Density 0.015%

    No Known Activations