© 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. 116292
    Prev
    Next
    INDEX
    Explanations

    foreign words and numbers

    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
     Both
    -0.08
    Both
    -0.07
     british
    -0.07
     cambi
    -0.06
     Aufl
    -0.06
     Harper
    -0.06
    대상
    -0.06
     영국
    -0.06
    英国
    -0.06
     British
    -0.06
    POSITIVE LOGITS
    inue
    0.08
     Muham
    0.06
     child
    0.06
    多次
    0.06
     rigidbody
    0.06
    यण
    0.06
     plusieurs
    0.06
     instaur
    0.06
     several
    0.06
     barric
    0.05
    Activations Density 0.034%

    No Known Activations