© 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. 116905
    Prev
    Next
    INDEX
    Explanations

    code structure or technical terms

    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
     не
    -0.08
     no
    -0.06
    กำ
    -0.06
     któ
    -0.06
     keine
    -0.06
     Gest
    -0.06
     does
    -0.06
    []
    -0.06
     которое
    -0.06
    是一位
    -0.06
    POSITIVE LOGITS
     feelings
    0.07
     specifying
    0.07
     même
    0.07
     حتی
    0.07
     even
    0.07
     상황
    0.06
    ोषित
    0.06
     rispetto
    0.06
     contemplating
    0.06
     photographic
    0.06
    Activations Density 0.001%

    No Known Activations