© 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. 119301
    Prev
    Next
    INDEX
    Explanations

    briefly followed by action or state

    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
    starttime
    -0.06
    裝置
    -0.05
     частина
    -0.05
    stress
    -0.05
     মানবিক
    -0.05
     ځای
    -0.05
     চল
    -0.05
    REW
    -0.05
     வழங்கும்
    -0.05
    æt
    -0.05
    POSITIVE LOGITS
    我
    0.07
     état
    0.07
     jeśli
    0.07
     Eigent
    0.06
     wanneer
    0.06
     если
    0.06
     zgodnie
    0.06
     Intake
    0.06
    我要
    0.06
     wenn
    0.06
    Activations Density 0.005%

    No Known Activations