© 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. 128455
    Prev
    Next
    INDEX
    Explanations

    move action

    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
     photospheric
    -0.06
     prezzi
    -0.06
     instead
    -0.06
    ancy
    -0.06
     origem
    -0.06
     Save
    -0.06
    phis
    -0.05
     euer
    -0.05
     fifties
    -0.05
     groe
    -0.05
    POSITIVE LOGITS
     awkwardly
    0.06
     tắc
    0.06
    私たち
    0.06
     routinely
    0.06
     dyslex
    0.06
     nude
    0.06
    孤独
    0.06
    हमें
    0.06
    舩
    0.06
     transnational
    0.05
    Activations Density 0.011%

    No Known Activations