© 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. 119273
    Prev
    Next
    INDEX
    Explanations

    names often followed by leaving

    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
     appears
    -0.07
     uncond
    -0.07
     времен
    -0.06
     এসেছে
    -0.06
    ((
    -0.06
     stub
    -0.06
     Tempor
    -0.06
    inline
    -0.06
     temporarily
    -0.06
     damaged
    -0.05
    POSITIVE LOGITS
    離開
    0.07
     deixar
    0.07
    离开
    0.07
     departing
    0.07
     trasferimento
    0.07
     departure
    0.07
    leaving
    0.06
     omissions
    0.06
     departed
    0.06
     Departure
    0.06
    Activations Density 0.014%

    No Known Activations