© 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. 119234
    Prev
    Next
    INDEX
    Explanations

    R

    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
     شمالی
    -0.06
    WebView
    -0.06
     blocs
    -0.05
     নীল
    -0.05
    color
    -0.05
     bölüm
    -0.05
    ೂರ್ವ
    -0.05
     biom
    -0.05
     выда
    -0.05
     imput
    -0.05
    POSITIVE LOGITS
     souvent
    0.07
     często
    0.07
     ditambah
    0.07
    のために
    0.06
     often
    0.06
    বক
    0.06
    Often
    0.06
     reserving
    0.06
     بیک
    0.06
    그리고
    0.06
    Activations Density 0.001%

    No Known Activations