© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117781
    Prev
    Next
    INDEX
    Explanations

    identifying information and requirements

    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
    了这个
    -0.07
     этому
    -0.06
     questo
    -0.06
    !.
    -0.06
     này
    -0.06
     #
    -0.06
     this
    -0.05
    alian
    -0.05
     цьому
    -0.05
     SUPER
    -0.05
    POSITIVE LOGITS
     grundsätzlich
    0.06
    钡
    0.06
    xception
    0.06
    ccccc
    0.06
    rául
    0.06
     каким
    0.06
     chiens
    0.06
    openjdk
    0.06
    特点
    0.06
    现在
    0.06
    Activations Density 0.001%

    No Known Activations