© 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. 128445
    Prev
    Next
    INDEX
    Explanations

    date citations

    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
     may
    -0.08
     může
    -0.07
     of
    -0.07
     può
    -0.06
     может
    -0.06
     może
    -0.06
     manifesting
    -0.06
     could
    -0.06
     who
    -0.06
     the
    -0.06
    POSITIVE LOGITS
     ventes
    0.06
     mnoho
    0.06
    versus
    0.06
     versus
    0.06
     fyrir
    0.06
     Kawasaki
    0.06
     kurulum
    0.06
    setColor
    0.06
     በጥ
    0.05
    summar
    0.05
    Activations Density 0.006%

    No Known Activations