© 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. 116995
    Prev
    Next
    INDEX
    Explanations

    after being tucked in bed

    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
     continuamente
    -0.06
     new
    -0.06
    随时
    -0.06
     Lax
    -0.06
     بحيث
    -0.05
     новая
    -0.05
     mobile
    -0.05
     revised
    -0.05
     timer
    -0.05
    ην
    -0.05
    POSITIVE LOGITS
     briefly
    0.08
     xong
    0.07
    接下来
    0.07
     wafers
    0.06
     पहले
    0.06
     breve
    0.06
     Gerr
    0.06
    暂时
    0.06
     cuore
    0.06
    ătur
    0.06
    Activations Density 0.023%

    No Known Activations