© 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. 129798
    Prev
    Next
    INDEX
    Explanations

    scientific abbreviations or initials

    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
    を
    -0.06
    াইবার
    -0.06
    天井
    -0.06
    इल
    -0.06
     thresholds
    -0.06
     in
    -0.06
    St
    -0.06
     тях
    -0.05
     St
    -0.05
     দুটো
    -0.05
    POSITIVE LOGITS
     শিক্ষার্থীরা
    0.07
     Perhaps
    0.07
    ForRule
    0.06
    transformed
    0.06
    Perhaps
    0.06
     μόνο
    0.06
     মনোযোগ
    0.06
     કંઈ
    0.06
     Thus
    0.06
     იქ
    0.06
    Activations Density 0.005%

    No Known Activations