© 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. 130278
    Prev
    Next
    INDEX
    Explanations

    copyright notice, disclaimer, conditions

    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
     as
    -0.09
     सितारों
    -0.08
    غ
    -0.07
     單
    -0.06
     sweatshirt
    -0.06
     gingham
    -0.06
     interfacing
    -0.06
     neces
    -0.06
    Jl
    -0.06
    тельных
    -0.06
    POSITIVE LOGITS
    ,
    0.07
     But
    0.06
    但
    0.06
     déclaré
    0.06
    কারে
    0.06
    也不会
    0.05
    ではなく
    0.05
     comprehensive
    0.05
    (_,
    0.05
    pm
    0.05
    Activations Density 0.002%

    No Known Activations