© 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. 128332
    Prev
    Next
    INDEX
    Explanations

    measurement instruments or topics

    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
    RIES
    -0.06
     tentando
    -0.06
     archiving
    -0.06
     rapp
    -0.06
    ayon
    -0.06
     býval
    -0.06
     soliciting
    -0.06
     torrential
    -0.06
    ovao
    -0.06
     Euh
    -0.05
    POSITIVE LOGITS
    льний
    0.07
    bases
    0.06
     bases
    0.06
     להיות
    0.06
     altered
    0.06
     coordinate
    0.06
     अधिक
    0.06
    Coord
    0.06
    ори
    0.06
     frames
    0.05
    Activations Density 0.002%

    No Known Activations