© 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. 129273
    Prev
    Next
    INDEX
    Explanations

    numbers and company names

    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
     نبود
    -0.06
     فرض
    -0.06
    痘
    -0.06
    uis
    -0.06
     forcing
    -0.06
     estimated
    -0.06
    Estim
    -0.06
     gara
    -0.06
    विदा
    -0.06
    遠
    -0.06
    POSITIVE LOGITS
     полного
    0.06
     Castle
    0.06
    Castle
    0.06
     అంటే
    0.06
     visit
    0.06
     castle
    0.06
    ையே
    0.06
     pancreatic
    0.06
    Comparative
    0.06
    ciato
    0.06
    Activations Density 0.040%

    No Known Activations