© 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. 129573
    Prev
    Next
    INDEX
    Explanations

    remove response, month, false

    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
    managers
    -0.06
     stanno
    -0.06
     вернуться
    -0.06
     はい
    -0.06
    themem
    -0.06
    نن
    -0.06
     manej
    -0.06
     reunir
    -0.06
     返回
    -0.06
     abordagem
    -0.06
    POSITIVE LOGITS
     if
    0.07
     dài
    0.06
    往往
    0.06
     Golden
    0.06
     what
    0.06
     Silver
    0.05
    local
    0.05
     считаю
    0.05
     solidar
    0.05
     reprodu
    0.05
    Activations Density 0.002%

    No Known Activations