© 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. 118881
    Prev
    Next
    INDEX
    Explanations

    such as examples

    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
    특히
    -0.06
    分类
    -0.06
    ಹಾರ
    -0.05
    必要がある
    -0.05
     لعب
    -0.05
     ebben
    -0.05
    镀
    -0.05
     চৈত
    -0.05
     связанных
    -0.05
    sonian
    -0.05
    POSITIVE LOGITS
     shows
    0.06
     reflects
    0.06
     তখনকার
    0.06
    보험
    0.06
     semantics
    0.06
     путем
    0.06
     توسط
    0.06
     showed
    0.06
     نشان
    0.06
    その
    0.06
    Activations Density 0.005%

    No Known Activations