© 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. 117138
    Prev
    Next
    INDEX
    Explanations

    I statements

    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
     nine
    -0.07
     ninety
    -0.07
    ９
    -0.07
     tři
    -0.06
    garten
    -0.06
    ８
    -0.06
    লাইয়া
    -0.06
     रहो
    -0.06
     eight
    -0.06
    ten
    -0.06
    POSITIVE LOGITS
    虽然
    0.07
     नेहमी
    0.06
    确实
    0.06
    雖然
    0.06
     잘
    0.06
     should
    0.06
     birçok
    0.06
     continued
    0.06
     will
    0.06
    確實
    0.06
    Activations Density 0.013%

    No Known Activations