© 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. 129494
    Prev
    Next
    INDEX
    Explanations

    in situ / initio generation / formation / structure / expression

    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
     (
    -0.07
    比如
    -0.06
     borrowed
    -0.06
     শহরের
    -0.06
     jointly
    -0.05
     @
    -0.05
          
    -0.05
     всеми
    -0.05
            
    -0.05
     long
    -0.05
    POSITIVE LOGITS
     Großbritannien
    0.08
    也在
    0.07
    GridLayout
    0.07
     sebenarnya
    0.07
    ẃ
    0.07
    EVEN
    0.07
     కూడా
    0.07
     também
    0.07
     sebagainya
    0.07
     terapé
    0.06
    Activations Density 0.011%

    No Known Activations