© 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. 120132
    Prev
    Next
    INDEX
    Explanations

    image references with caption markers

    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
    ,.
    -0.07
     slightly
    -0.07
     légèrement
    -0.06
     récemment
    -0.06
     complies
    -0.06
     이차
    -0.06
     damned
    -0.06
     கிழ
    -0.06
    '_
    -0.06
     famille
    -0.06
    POSITIVE LOGITS
    Provides
    0.07
     including
    0.06
    内的
    0.06
     के
    0.06
     providing
    0.06
     provides
    0.06
     alcuni
    0.06
    Scala
    0.06
     பொருளாதார
    0.06
     joins
    0.06
    Activations Density 0.001%

    No Known Activations