© 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. 116777
    Prev
    Next
    INDEX
    Explanations

    control algorithm

    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
    合适
    -0.07
     Без
    -0.07
     abbat
    -0.06
     accepter
    -0.06
     Appear
    -0.06
     Imaging
    -0.06
     동일
    -0.06
     býval
    -0.06
     MenuView
    -0.06
     एप्ली
    -0.06
    POSITIVE LOGITS
     the
    0.07
     শনিবার
    0.06
     নম্বর
    0.06
    सेवी
    0.06
     modifiers
    0.05
     trò
    0.05
    WebGL
    0.05
     Plus
    0.05
     Tw
    0.05
    യുടെ
    0.05
    Activations Density 0.003%

    No Known Activations