© 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. 117683
    Prev
    Next
    INDEX
    Explanations

    quotation marks or apostrophes encapsulating words

    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
     Some
    -0.07
    、
    -0.07
     housekeeping
    -0.07
     either
    -0.06
     noteworthy
    -0.06
    かもしれない
    -0.06
     some
    -0.06
     unbelievably
    -0.06
     belated
    -0.06
     there
    -0.06
    POSITIVE LOGITS
     সর্বনিম্ন
    0.06
     Kins
    0.06
    ourcing
    0.06
     هر
    0.06
    但
    0.05
     قدرت
    0.05
     sourcing
    0.05
    这些
    0.05
     parcour
    0.05
    這些
    0.05
    Activations Density 0.010%

    No Known Activations