© 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. 128374
    Prev
    Next
    INDEX
    Explanations

    filename, path, URL

    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
     این
    -0.08
     this
    -0.07
     THIS
    -0.07
     този
    -0.07
     questa
    -0.06
     это
    -0.06
     دانشگاه
    -0.06
     этом
    -0.06
     possibili
    -0.06
     guru
    -0.06
    POSITIVE LOGITS
     স্বাভাবিক
    0.05
    elian
    0.05
    လ
    0.05
     मिन
    0.05
    -------------
    0.05
    urilor
    0.05
     alternative
    0.05
    getDoctrine
    0.05
    ড়িয়ে
    0.05
     unrivalled
    0.05
    Activations Density 0.006%

    No Known Activations