© 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. 120609
    Prev
    Next
    INDEX
    Explanations

    as far as I know

    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
     फीट
    -0.06
    FieldValue
    -0.06
     may
    -0.06
     какого
    -0.06
     various
    -0.06
    malıdır
    -0.06
     проведение
    -0.06
     каких
    -0.06
     Last
    -0.06
     some
    -0.06
    POSITIVE LOGITS
     keadaan
    0.06
    டியா
    0.06
     가운데
    0.06
    決して
    0.06
     système
    0.06
     система
    0.05
     đều
    0.05
     Система
    0.05
     کی
    0.05
     NÃO
    0.05
    Activations Density 0.028%

    No Known Activations