© 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. 119553
    Prev
    Next
    INDEX
    Explanations

    UI component names

    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
     значит
    -0.06
     innen
    -0.06
    采访
    -0.06
     [{
    -0.06
     buffer
    -0.06
     vetted
    -0.06
     అనే
    -0.06
     large
    -0.06
     theoretical
    -0.06
    ደት
    -0.05
    POSITIVE LOGITS
     régulière
    0.06
    以往
    0.06
     steep
    0.06
     repeated
    0.06
     Regular
    0.06
     skład
    0.05
     discontinue
    0.05
    നിക്ക
    0.05
     ši
    0.05
     ছড়িয়ে
    0.05
    Activations Density 0.002%

    No Known Activations