© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118205
    Prev
    Next
    INDEX
    Explanations

    leaving or departing

    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
     began
    -0.07
     profits
    -0.06
     started
    -0.06
     novel
    -0.06
    ास
    -0.06
    Utilization
    -0.06
    Lever
    -0.06
    Holding
    -0.06
     possibility
    -0.06
     vah
    -0.06
    POSITIVE LOGITS
     departing
    0.08
     outgoing
    0.07
     parting
    0.07
     시간을
    0.06
     goodbye
    0.06
     pausing
    0.06
     Departure
    0.06
     уй
    0.06
     resistant
    0.06
     시간이
    0.06
    Activations Density 0.033%

    No Known Activations