© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130008
    Prev
    Next
    INDEX
    Explanations

    destroyed by fire

    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
     sebelum
    -0.06
     healthier
    -0.06
    iles
    -0.06
     heartbreaking
    -0.06
     misleading
    -0.06
    ТС
    -0.06
     విషయంలో
    -0.06
     before
    -0.06
    rick
    -0.06
     себе
    -0.05
    POSITIVE LOGITS
     india
    0.06
     independ
    0.06
    loaded
    0.06
     reson
    0.06
     introduces
    0.06
     muchas
    0.06
     relaxes
    0.06
     расположены
    0.06
     Isabella
    0.06
     tenets
    0.06
    Activations Density 0.010%

    No Known Activations