© 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. 129796
    Prev
    Next
    INDEX
    Explanations

    date, GPS, option, communication

    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
     other
    -0.07
    ,
    -0.06
    ston
    -0.06
    ino
    -0.06
    str
    -0.05
     także
    -0.05
     that
    -0.05
     also
    -0.05
     PP
    -0.05
     अन्य
    -0.05
    POSITIVE LOGITS
     criação
    0.08
     walaupun
    0.07
     онлайн
    0.07
     gruppi
    0.07
     каждой
    0.07
     এই
    0.07
    chelles
    0.07
     köpek
    0.07
     hewan
    0.06
    ———
    0.06
    Activations Density 0.002%

    No Known Activations