© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118606
    Prev
    Next
    INDEX
    Explanations

    IP address, URLs, or version 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
     gigantic
    -0.08
     wird
    -0.07
     não
    -0.06
     demonstrates
    -0.06
     embodies
    -0.06
     enormous
    -0.06
     degli
    -0.06
     میلیون
    -0.06
     extraordinarily
    -0.06
     illustrates
    -0.06
    POSITIVE LOGITS
    各
    0.06
    䣵
    0.06
     Hud
    0.06
    Hud
    0.05
     GAAP
    0.05
     грошы
    0.05
    ���
    0.05
     Developments
    0.05
    型的
    0.05
     razvoja
    0.05
    Activations Density 0.083%

    No Known Activations