© 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. 129364
    Prev
    Next
    INDEX
    Explanations

    numbers and specific 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
     certains
    -0.08
    certain
    -0.06
     સ્વા
    -0.06
     certaines
    -0.06
     selectivity
    -0.06
     nég
    -0.06
    ধ্য
    -0.06
     sizes
    -0.06
     You
    -0.06
     każdy
    -0.06
    POSITIVE LOGITS
     beispielsweise
    0.06
    legislation
    0.06
    ใน
    0.06
                     
    0.06
    堞
    0.06
    fecture
    0.06
     in
    0.06
     distinctive
    0.06
     überhaupt
    0.06
     notably
    0.05
    Activations Density 0.001%

    No Known Activations