© 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. 128507
    Prev
    Next
    INDEX
    Explanations

    code setup or declaration

    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
     enterprising
    -0.07
     गन्ना
    -0.06
     ambitious
    -0.06
     tagline
    -0.06
    ellia
    -0.06
     toz
    -0.06
     intricate
    -0.06
     ingenious
    -0.06
     inizi
    -0.06
    5
    -0.06
    POSITIVE LOGITS
    에는
    0.08
     필
    0.07
    Apply
    0.06
     Función
    0.06
    Effective
    0.06
    deutsche
    0.06
    apply
    0.06
    确认
    0.06
     suddenly
    0.06
     recentemente
    0.06
    Activations Density 0.008%

    No Known Activations