© 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. 129071
    Prev
    Next
    INDEX
    Explanations

    php database connection code

    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
     misalnya
    -0.07
    了吗
    -0.07
     интересу
    -0.06
     esimerkiksi
    -0.06
    форми
    -0.06
     после
    -0.06
    amiseks
    -0.06
     например
    -0.06
     pledge
    -0.06
     initially
    -0.06
    POSITIVE LOGITS
    Applic
    0.06
     జరుగు
    0.06
    appan
    0.06
     varie
    0.06
     misc
    0.06
     ലീ
    0.06
    প্রধান
    0.05
     PSOE
    0.05
     рестора
    0.05
     Misc
    0.05
    Activations Density 0.010%

    No Known Activations