© 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. 128414
    Prev
    Next
    INDEX
    Explanations

    notifications and notices

    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
     your
    -0.08
    你的
    -0.07
    您的
    -0.07
     ваших
    -0.07
    あなたの
    -0.07
     ваша
    -0.07
     அல்லது
    -0.07
     вашего
    -0.06
    your
    -0.06
     вам
    -0.06
    POSITIVE LOGITS
     
    0.07
    multirow
    0.06
     इवेंट
    0.06
     exempel
    0.06
     RSVP
    0.06
     répartition
    0.06
    利
    0.06
     raffle
    0.06
     ubicación
    0.06
    harga
    0.05
    Activations Density 0.053%

    No Known Activations