© 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. 120472
    Prev
    Next
    INDEX
    Explanations

    verbs before "out", "–", "Runner", ":", "Line"

    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
     Н
    -0.06
     Helpful
    -0.06
     tient
    -0.06
    绣
    -0.06
    褶
    -0.06
    ]*
    -0.06
     later
    -0.06
     своё
    -0.06
    grip
    -0.05
     Jacobian
    -0.05
    POSITIVE LOGITS
     المسي
    0.07
     ක
    0.07
     guitar
    0.07
     guitarra
    0.07
     Fibonacci
    0.06
    越來越
    0.06
    響
    0.06
    寐
    0.06
    Filtered
    0.06
     teclado
    0.06
    Activations Density 0.001%

    No Known Activations