© 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. 119233
    Prev
    Next
    INDEX
    Explanations

    quoting or bracketing code structure

    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
     OPTIONS
    -0.07
     misschien
    -0.07
    ,
    -0.06
     perhaps
    -0.06
     possibly
    -0.06
     มี
    -0.06
    ",
    -0.06
     acknowledged
    -0.06
    可能是
    -0.06
    Выберите
    -0.06
    POSITIVE LOGITS
     ogrom
    0.06
     add
    0.06
     outline
    0.06
     huge
    0.06
     bzw
    0.06
    splitLength
    0.06
    only
    0.06
     outlines
    0.05
    로는
    0.05
     irrepar
    0.05
    Activations Density 0.004%

    No Known Activations