© 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. 116335
    Prev
    Next
    INDEX
    Explanations

    titles, names, and descriptions

    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
    电视台
    -0.06
     protagon
    -0.06
    中的
    -0.06
    给我们
    -0.06
     koy
    -0.06
     главный
    -0.06
     stresses
    -0.06
    邑
    -0.06
    สังคม
    -0.06
     momentum
    -0.06
    POSITIVE LOGITS
     трех
    0.06
     Cancell
    0.06
     Ferien
    0.06
     kleinen
    0.06
     privately
    0.06
     иногда
    0.06
    Karena
    0.06
     directa
    0.06
     zog
    0.05
     entró
    0.05
    Activations Density 0.015%

    No Known Activations