© 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. 128638
    Prev
    Next
    INDEX
    Explanations

    closing parentheses followed by AS

    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
    .
    -0.08
     così
    -0.06
     kawaida
    -0.06
    कस
    -0.06
     आजही
    -0.06
     عندما
    -0.06
     بحيث
    -0.06
    中医
    -0.06
    .!
    -0.06
     gdje
    -0.06
    POSITIVE LOGITS
     to
    0.07
     bessere
    0.06
     is
    0.06
     better
    0.06
    名为
    0.06
     miglior
    0.06
     einzige
    0.06
     will
    0.06
     अधिकतर
    0.06
    都不是
    0.06
    Activations Density 0.004%

    No Known Activations