© 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. 128577
    Prev
    Next
    INDEX
    Explanations

    timestamps such as numbers

    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
     Disbursement
    -0.06
     Indicate
    -0.06
    สอง
    -0.06
     उपायों
    -0.05
     উল
    -0.05
     sovi
    -0.05
     втори
    -0.05
     Assigned
    -0.05
    ნენ
    -0.05
    ভগ
    -0.05
    POSITIVE LOGITS
     Suche
    0.07
     television
    0.06
     দর্শক
    0.06
    Such
    0.06
     देखें
    0.06
     بالإضافة
    0.06
     SUCH
    0.06
     the
    0.06
    ggac
    0.06
    ının
    0.05
    Activations Density 0.001%

    No Known Activations