© 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. 119030
    Prev
    Next
    INDEX
    Explanations

    html meta tags

    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
    ggplot
    -0.06
     iniciando
    -0.06
     promised
    -0.06
    initializing
    -0.05
     Vereins
    -0.05
    就很
    -0.05
    utory
    -0.05
    กับ
    -0.05
    など
    -0.05
    Rachel
    -0.05
    POSITIVE LOGITS
     būti
    0.07
    들에게
    0.07
     возможность
    0.06
     extensive
    0.06
     সরাসরি
    0.06
     essere
    0.06
    分别是
    0.06
    چان
    0.06
    들에
    0.06
     Ă
    0.06
    Activations Density 0.001%

    No Known Activations