© 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. 116988
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    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
     після
    -0.07
     наиболее
    -0.07
     saut
    -0.07
     zusätzlich
    -0.06
     Это
    -0.06
     zudem
    -0.06
     tremendously
    -0.06
    நிலைய
    -0.06
     после
    -0.06
     tendencia
    -0.06
    POSITIVE LOGITS
     ARCH
    0.06
     ######
    0.06
     ach
    0.06
     trabalh
    0.05
     &:
    0.05
    㓩
    0.05
     you
    0.05
    /',
    0.05
    ...?
    0.05
    &-
    0.05
    Activations Density 0.006%

    No Known Activations