© 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. 116577
    Prev
    Next
    INDEX
    Explanations

    Q:

    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
     worrisome
    -0.06
    之前
    -0.06
     normalerweise
    -0.06
     itp
    -0.06
     remarkably
    -0.06
     noteworthy
    -0.06
     pristine
    -0.06
     dazzling
    -0.06
     wondrous
    -0.06
     important
    -0.06
    POSITIVE LOGITS
     estratégico
    0.06
    ாச
    0.06
     technique
    0.06
     '!
    0.06
     수익
    0.06
    airobi
    0.06
     the
    0.06
    CopyTo
    0.06
    authorize
    0.06
     metodi
    0.06
    Activations Density 0.001%

    No Known Activations