© 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. 119732
    Prev
    Next
    INDEX
    Explanations

    the end of a sentence or phrase

    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
    heated
    -0.06
    灼
    -0.05
    пуляр
    -0.05
     क्वा
    -0.05
    𝒉
    -0.05
    backpack
    -0.05
    ськ
    -0.05
     damaging
    -0.05
    Position
    -0.05
     behand
    -0.05
    POSITIVE LOGITS
     здесь
    0.07
     softer
    0.06
    '')
    0.06
     πάντα
    0.06
     टच
    0.06
     seç
    0.06
    ಸಿದ
    0.06
    いわ
    0.06
     ähn
    0.06
     Within
    0.06
    Activations Density 0.086%

    No Known Activations