© 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. 117692
    Prev
    Next
    INDEX
    Explanations

    css, Toolkit, lesions, Valley

    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
     여름
    -0.07
     successivamente
    -0.07
    iguo
    -0.07
     bolognese
    -0.06
     vibrations
    -0.06
     Quỳnh
    -0.06
     어머니
    -0.06
     ошибок
    -0.06
     alles
    -0.06
     Hawking
    -0.06
    POSITIVE LOGITS
     five
    0.08
     more
    0.06
    е
    0.06
    rystal
    0.06
     not
    0.05
     recorded
    0.05
    five
    0.05
     has
    0.05
     four
    0.05
     remain
    0.05
    Activations Density 0.004%

    No Known Activations