© 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. 128953
    Prev
    Next
    INDEX
    Explanations

    variable and value declarations

    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
     его
    -0.08
    他的
    -0.07
    它的
    -0.07
    他在
    -0.07
    频繁
    -0.06
     그의
    -0.06
     jego
    -0.06
     esta
    -0.06
     njegov
    -0.06
     unnatural
    -0.06
    POSITIVE LOGITS
     the
    0.08
    時点で
    0.06
     Columns
    0.06
     by
    0.06
    ovaných
    0.06
     वास्तविकता
    0.06
    ಪಡ
    0.06
     The
    0.05
     Hence
    0.05
    することにより
    0.05
    Activations Density 0.006%

    No Known Activations