© 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. 128822
    Prev
    Next
    INDEX
    Explanations

    condition or clause boundaries

    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
    ｡
    -0.06
     人気
    -0.05
     simplified
    -0.05
     জাগ
    -0.05
                 
    -0.05
     scenic
    -0.05
    這
    -0.05
     felicit
    -0.05
     বয়সী
    -0.05
     making
    -0.05
    POSITIVE LOGITS
     if
    0.07
     under
    0.07
     från
    0.07
     When
    0.07
    两者
    0.07
     när
    0.07
     when
    0.07
     by
    0.07
     between
    0.06
     трёх
    0.06
    Activations Density 0.012%

    No Known Activations