© 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. 129105
    Prev
    Next
    INDEX
    Explanations

    query or dates

    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
    ক্রিয়
    -0.07
    Then
    -0.07
    finement
    -0.06
     nende
    -0.06
     blog
    -0.06
     Then
    -0.06
     этими
    -0.06
    챔
    -0.06
    limiting
    -0.06
     faccio
    -0.06
    POSITIVE LOGITS
     que
    0.06
    .[
    0.05
     살펴보도록
    0.05
    ,
    0.05
    QUERY
    0.05
    Hey
    0.05
    ul
    0.05
     Query
    0.05
    ropshire
    0.05
     Luxemburg
    0.05
    Activations Density 0.010%

    No Known Activations